From ee3d7ba75abf4348d6b4b447b4f275f75054d665 Mon Sep 17 00:00:00 2001 From: opencode-go-evals Date: Mon, 9 Nov 2026 05:24:26 +0000 Subject: [PATCH] chore: weekly evaluation refresh 2026-11-09 --- MODELS.md | 406 ++++----- site/assets/catalog.js | 1035 +++++++++++----------- site/assets/evals.js | 1696 +++++++++++++++++++------------------ site/assets/history.js | 24 + site/assets/history.json | 24 + site/assets/snapshot.json | 421 +++++---- 6 files changed, 1835 insertions(+), 1771 deletions(-) diff --git a/MODELS.md b/MODELS.md index a71a82c..30864cb 100644 --- a/MODELS.md +++ b/MODELS.md @@ -5,7 +5,7 @@ Short, practical notes on every model in the OpenCode Go catalogue: what each on what it costs, and what to watch out for. Evaluated scores come from Artificial Analysis (single consistent harness) plus vendor model cards. -Catalogue metadata comes from models.dev's OpenCode Go provider. Data snapshot: **2026-11-02**. +Catalogue metadata comes from models.dev's OpenCode Go provider. Data snapshot: **2026-11-09**. The interactive version with the full task matrix lives at `site/index.html`. > No model in the Go catalogue generates images. Every Go model is text-output; several accept image, @@ -28,16 +28,6 @@ The interactive version with the full task matrix lives at `site/index.html`. ### undefined -**google** · released 2026-10-13 · $2 in / $10 out per 1M tokens · 1.05M context · text, image, video, audio, pdf in → text out - -Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents - -_No hand-written write-up yet._ - -*Evaluated:* Intelligence Index 50.4 · FrontierCode 43.5 · TB4.0 57.1 · AutomationBench 77.5 · HLE 57.1 · LCR 79.7 - -### undefined - **google** · released 2026-10-13 · $4 in / $20 out per 1M tokens · 1.05M context · text, image, video, audio, pdf in → text out Targeted for: **Frontier coding, Deep research, Legal & financial work, Security, Multimodal** @@ -56,13 +46,23 @@ Hardest frontier work: large codebase refactors and optimisation (Google used it ### undefined +**google** · released 2026-10-13 · $2 in / $10 out per 1M tokens · 1.05M context · text, image, video, audio, pdf in → text out + +Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents + +_No hand-written write-up yet._ + +*Evaluated:* Intelligence Index 50.4 · FrontierCode 43.5 · TB4.0 57.1 · AutomationBench 77.5 · HLE 57.1 · LCR 79.7 + +### undefined + **moonshotai** · released 2026-10-23 · $2 in / $10 out per 1M tokens · 1.05M context · text, image, video in → text out Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work _No hand-written write-up yet._ -*Evaluated:* Intelligence Index 46 · FrontierCode 47.1 · TB4.0 67.2 · AutomationBench 73.3 · HLE 52.5 · LCR 86.3 · MMMU-Pro 83.9 +*Evaluated:* Intelligence Index 46.5 · FrontierCode 47.1 · TB4.0 67.2 · AutomationBench 73.3 · HLE 52.5 · LCR 86.3 · MMMU-Pro 83.9 ### undefined @@ -74,7 +74,7 @@ Meta's multimodal reasoning model for long-running agentic, multi-agent and codi Multi-agent and long-horizon pipelines: several specialised agents handing work to each other over a 1M window, with the widest input surface in Go (image, video, PDF and audio all accepted). Cheap enough ($0.10 / $0.20) to keep several agents running at once — it is the pick when the architecture, not the single call, is doing the work. -*Evaluated:* Intelligence Index 36.4 · FrontierCode 40.6 · TB2.1 84.3 · AutomationBench 57.9 · GPQA 93.5 · HLE 48.7 · LCR 83 +*Evaluated:* Intelligence Index 36.6 · FrontierCode 40.6 · TB2.1 84.3 · AutomationBench 57.9 · GPQA 93.5 · HLE 48.7 · LCR 83 **Caveats** @@ -91,7 +91,7 @@ Fast Claude model for responsive assistance, classification, and lightweight age Anything that has to answer fast and often: interactive completions, classification and extraction, lightweight sub-agents, and UI-style assistance where latency matters more than depth. Anthropic's tool-calling behaviour is the draw for lightweight agents. -*Evaluated:* Intelligence Index 36.2 · FrontierCode 41.8 · TB4.0 32.8 · AutomationBench 35.4 · HLE 44.4 · LCR 82.7 +*Evaluated:* Intelligence Index 36.5 · FrontierCode 41.8 · TB4.0 32.8 · AutomationBench 35.4 · HLE 44.4 · LCR 82.7 **Caveats** @@ -108,7 +108,7 @@ xAI's frontier model for long-running agents, coding, knowledge work, and visual Sustained agent sessions that mix code and document/visual inputs — research that ends in a written deliverable, codebase work with images in the loop, or an analysis that has to survive a long run without losing the thread. Priced at the top of the open-model tier but with a 500K window that suits multi-file, multi-hour tasks. -*Evaluated:* Intelligence Index 34.3 · FrontierCode 33.8 · TB4.0 25.8 · AutomationBench 65.6 · HLE 43.1 · LCR 76.7 +*Evaluated:* Intelligence Index 35.5 · FrontierCode 33.8 · TB4.0 25.8 · AutomationBench 65.6 · HLE 43.1 · LCR 76.7 **Caveats** @@ -125,7 +125,7 @@ A 2.4-trillion-parameter MoE flagship for coding, professional work, multimodal Broad, heavy-duty work where a single model has to cover the whole job: writing code, producing professional deliverables (the GDPval/JobBench scores are strong), and reasoning over images, video and PDFs in the same session. Also the strongest general agent in Go on the terminal and tool-use benchmarks. -*Evaluated:* Intelligence Index 33.6 · FrontierCode 43.2 · TB2.1 88.8 · AutomationBench 56.2 · GPQA 92.8 · HLE 43.1 · LCR 80.3 · MMMU-Pro 82.8 +*Evaluated:* Intelligence Index 33.7 · FrontierCode 43.2 · TB2.1 88.8 · AutomationBench 56.2 · GPQA 92.8 · HLE 43.1 · LCR 80.3 · MMMU-Pro 82.8 **Caveats** @@ -168,6 +168,16 @@ Coding agents that also have to look at things: screenshots, video, audio alongs ### undefined +**minimax** · released 2026-10-19 · $0.15 in / $0.6 out per 1M tokens · 1M context · text, image, video in → text out + +Frontier multimodal coding model with 1M context window and tunable thinking depth + +_No hand-written write-up yet._ + +*Evaluated:* Intelligence Index 29.1 · FrontierCode 38.6 · TB4.0 25.8 · AutomationBench 72.5 · HLE 48 · LCR 79.7 · MMMU-Pro 79.1 + +### undefined + **minimax** · released 2026-10-19 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 1M context · text, image, video in → text out Targeted for: **Coding, Multimodal, Agentic, Free tier** @@ -176,7 +186,7 @@ Frontier multimodal coding model with a 1M-token context window and tunable thin Day-to-day coding-agent work on real repositories: reading long codebases, editing files, running tools. Image and video input make it usable for UI/screenshot-driven work (reading a rendered page, describing an asset). Because thinking depth is tunable, it can be dialed down for cheap, high-volume turns and up for hard problems. -*Evaluated:* Intelligence Index 28.9 · FrontierCode 38.6 · TB4.0 25.8 · AutomationBench 72.5 · HLE 48 · LCR 79.7 · MMMU-Pro 79.1 +*Evaluated:* Intelligence Index 29.1 · FrontierCode 38.6 · TB4.0 25.8 · AutomationBench 72.5 · HLE 48 · LCR 79.7 · MMMU-Pro 79.1 **Caveats** @@ -185,16 +195,6 @@ Day-to-day coding-agent work on real repositories: reading long codebases, editi ### undefined -**minimax** · released 2026-10-19 · $0.15 in / $0.6 out per 1M tokens · 1M context · text, image, video in → text out - -Frontier multimodal coding model with 1M context window and tunable thinking depth - -_No hand-written write-up yet._ - -*Evaluated:* Intelligence Index 28.9 · FrontierCode 38.6 · TB4.0 25.8 · AutomationBench 72.5 · HLE 48 · LCR 79.7 · MMMU-Pro 79.1 - -### undefined - **stepfun** · released 2026-09-16 · $1 in / $2.7 out per 1M tokens · 1M context · text, image, video in → text out Targeted for: **Coding, Professional knowledge work, Multimodal, Open weights** @@ -212,6 +212,23 @@ Coding plus deliverables: a base model strong enough to write production code an ### undefined +**openai** · released 2026-09-22 · $0.1 in / $0.5 out per 1M tokens · 1.05M context · text, image, pdf in → text out + +Targeted for: **High-volume coding, Agents, Document work, Cheap** + +OpenAI's most efficient model for focused, high-volume tasks, at the price of a small open model. + +The default workhorse when you want GPT-class behaviour without GPT-class spend: everyday coding-agent turns, small refactors, summarising long documents (1.05M window), classifying and routing. In Go it is one of the best price/performance points, so it is a good default for background agents and a fallback when a heavier model is unnecessary. + +*Evaluated:* Intelligence Index 27.9 · FrontierCode 41.9 · TB4.0 12.6 · AutomationBench 53.2 · HLE 38.5 · LCR 83.3 · MMMU-Pro 79.7 + +**Caveats** + +- Price steps up above 272K tokens of context. +- Not a reasoning-tier model — deep analysis work should go to a stronger model. + +### undefined + **zhipuai** · released 2026-08-26 · $0.15 in / $0.5 out per 1M tokens · 1M context · text, image, video in → text out Targeted for: **Efficient coding, Long-horizon agents, Multimodal, Cheap** @@ -229,23 +246,6 @@ The cheap twin of the flagship: same family behaviour, multimodal input, and one ### undefined -**openai** · released 2026-09-22 · $0.1 in / $0.5 out per 1M tokens · 1.05M context · text, image, pdf in → text out - -Targeted for: **High-volume coding, Agents, Document work, Cheap** - -OpenAI's most efficient model for focused, high-volume tasks, at the price of a small open model. - -The default workhorse when you want GPT-class behaviour without GPT-class spend: everyday coding-agent turns, small refactors, summarising long documents (1.05M window), classifying and routing. In Go it is one of the best price/performance points, so it is a good default for background agents and a fallback when a heavier model is unnecessary. - -*Evaluated:* Intelligence Index 27.8 · FrontierCode 41.9 · TB4.0 12.6 · AutomationBench 53.2 · HLE 38.5 · LCR 83.3 · MMMU-Pro 79.7 - -**Caveats** - -- Price steps up above 272K tokens of context. -- Not a reasoning-tier model — deep analysis work should go to a stronger model. - -### undefined - **xiaomi** · released 2026-09-22 · $0.14 in / $0.28 out per 1M tokens · 1.05M context · text, image, audio, video in → text out Targeted for: **Cheap, Multimodal, Automation, Coding agents** @@ -263,6 +263,22 @@ The cheapest multimodal agent in Go at 14¢/28¢ per 1M: bulk automation over lo ### undefined +**openai** · released 2026-07-09 · $0.2 in / $1.2 out per 1M tokens · 1.05M context · text, image, pdf in → text out + +Targeted for: **Fast & cheap, High-volume coding, Agents** + +Cost-efficient GPT-5.6 model for fast, high-volume workloads. + +Throughput work: many small calls, classification, extraction, routing and repetitive edits where latency and cost per call decide the outcome. Keeps the GPT tool-calling behaviour at roughly twice the price of GPT-6 Luna. + +*Evaluated:* Intelligence Index 23.8 · TB2.1 80.9 · AutomationBench 50.2 · GPQA 91.1 · HLE 39.5 · LCR 83.7 · MMMU-Pro 78.6 + +**Caveats** + +- Price steps up above 272K tokens of context. + +### undefined + **deepseek** · released 2026-04-24 · $0.66 in / $1.98 out per 1M tokens · 1M context · text in → text out Targeted for: **Long agent runs, Coding, Math & science, Open weights** @@ -288,7 +304,7 @@ MiniMax multimodal model for long-context coding, perception, and agent planning Repo-scale SWE work with perception in the loop: MiniMax reports one of the strongest SWE-Bench Verified results in Go, plus good browser and desktop-computer scores (BrowseComp, MCP Atlas, OSWorld). Use it when the agent has to look at a screen and then change code. -*Evaluated:* Intelligence Index 18.7 · FrontierCode 23 · TB2.1 65.2 · AutomationBench 21.3 · GPQA 92.9 · HLE 39 · LCR 83 · MMMU-Pro 78.6 +*Evaluated:* Intelligence Index 18.9 · FrontierCode 23 · TB2.1 65.2 · AutomationBench 21.3 · GPQA 92.9 · HLE 39 · LCR 83 · MMMU-Pro 78.6 **Caveats** @@ -314,6 +330,58 @@ Cost-efficient coding and agent loops. The MoE design activates only 23B paramet ### undefined +**deepseek** · released 2026-09-10 · $0.15 in / $0.6 out per 1M tokens · 1M context · text, image in → text out + +Targeted for: **Agentic coding, Reasoning, Cheap, High volume** + +DeepSeek's V4.1 Flash: built for reasoning and agentic coding, and the single most-used model in OpenCode by token volume. + +The default engine for long coding-agent runs. DeepSeek's own card lists Terminal-Bench, DeepSWE, CyberGym and AutomationBench scores, i.e. it is tuned for terminal work, repo-level fixes and security tasks rather than chat. With cache reads at ~0.3¢/1M it is also the cheapest way to move large volumes of agent traffic. + +*Evaluated:* no public third-party evaluation published yet. + +**Caveats** + +- Text output only. +- Price doubles during DeepSeek's peak hours (01:00–04:00 and 06:00–10:00 UTC, Mon–Fri). + +### undefined + +**alibaba** · released 2026-08-26 · $0.15 in / $0.47 out per 1M tokens · 1M context · text, image, video in → text out + +Targeted for: **Visual reasoning, Documents, Agent tasks, Cheap** + +Qwen vision-language model for visual reasoning, documents, and agent tasks. + +Perception-heavy work at a low price: reading screenshots and diagrams, extracting from documents, and driving agents that need to see what is on screen. It pairs a 1M window with sub-20¢ input pricing, which makes it a good bulk worker for visual pipelines. + +*Evaluated:* no public third-party evaluation published yet. + +**Caveats** + +- Text output only — no image generation. +- Evaluated publicly as 'Qwen3.8-Flash-Next' in third-party benchmark tables. + +### undefined + +**meituan** · released 2026-09-25 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 1M context · text, image in → text out + +Targeted for: **Coding, Agentic, Image understanding, Free tier** + +Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window. + +Agents that have to read a picture to act: UI automation, screenshot-to-code, chart and document understanding, then long runs of tool use against a 1M-token window. Pairs well with a free-tier workflow — long exploratory sessions without burning a paid model's allowance. + +*Evaluated:* no public third-party evaluation published yet. + +**Caveats** + +- Free for a limited time. +- Preview release: scores and behaviour may shift. +- Text output only — no image generation. + +### undefined + **alibaba** · released 2026-06-02 · $0.4 in / $1.6 out per 1M tokens · 1M context · text, image, video in → text out Targeted for: **Long-context agents, Visual inputs, Coding, Multimodal** @@ -331,36 +399,37 @@ A steady middle tier: long-context agent sessions, image/video understanding and ### undefined -**stepfun** · released 2026-09-16 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 1M context · text, image, video in → text out +**undisclosed** · released 2026-09-23 · $0.15 in / $0.6 out per 1M tokens · 1.05M context · text, image, video in → text out -Targeted for: **Free tier, Coding, Professional knowledge work, Multimodal** +Targeted for: **Coding, Agentic tasks, Tool use, Multimodal** -Free access to StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image and video input and a 1M-token context window. +Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input. -Same model as the paid Step 5 Preview, without the token bill — useful for long agent runs and multimodal work while the paid allowance is reserved for the hard tasks. +An unreleased preview model with full multimodal input and tool use, priced like the value tier. It has no vendor behind it and no public evaluation, so treat it as an experiment rather than a recommendation. *Evaluated:* no public third-party evaluation published yet. **Caveats** -- Limited-time free entry; not present in the live Go catalogue endpoint, so availability may vary. +- No vendor or model card — no published evaluation. +- Not listed in the live Go catalogue endpoint. ### undefined -**tencent** · released 2026-08-28 · $0.834 in / $2.501 out per 1M tokens · 1.02M context · text in → text out +**xiaomi** · released 2026-04-22 · $0.14 in / $0.28 out per 1M tokens · 1M context · text, image, audio, video in → text out -Targeted for: **Agentic workflows, Productivity, Complex task execution, Open weights** +Targeted for: **Budget multimodal agents, Long context** -A next-generation productivity model with significantly enhanced agent and complex task execution capabilities. +Open MiMo model for multimodal coding agents and long-context automation. -Productivity and workflow automation: multi-step office/enterprise tasks, tool orchestration and long-running assistants. Tencent positions it around agentic capability and complex task execution rather than raw chat quality, with a 1M window for large corpora. +The cheapest way to get multimodal, long-context agent behaviour in Go: 14¢/28¢ per 1M. Best suited to bulk automation — many small steps over a large context — rather than to hard single-shot questions. *Evaluated:* no public third-party evaluation published yet. **Caveats** -- Preview release with no third-party evaluations published yet, so performance is unverified outside the vendor's own numbers. -- Text input only. +- Lowest tier of the MiMo line; weak on the hardest agentic benchmarks. +- Text output only. ### undefined @@ -381,20 +450,37 @@ An anonymous free tier aimed at agents: tool calling and structured JSON output ### undefined -**alibaba** · released 2026-08-26 · $0.15 in / $0.47 out per 1M tokens · 1M context · text, image, video in → text out +**tencent** · released 2026-08-28 · $0.834 in / $2.501 out per 1M tokens · 1.02M context · text in → text out -Targeted for: **Visual reasoning, Documents, Agent tasks, Cheap** +Targeted for: **Agentic workflows, Productivity, Complex task execution, Open weights** -Qwen vision-language model for visual reasoning, documents, and agent tasks. +A next-generation productivity model with significantly enhanced agent and complex task execution capabilities. -Perception-heavy work at a low price: reading screenshots and diagrams, extracting from documents, and driving agents that need to see what is on screen. It pairs a 1M window with sub-20¢ input pricing, which makes it a good bulk worker for visual pipelines. +Productivity and workflow automation: multi-step office/enterprise tasks, tool orchestration and long-running assistants. Tencent positions it around agentic capability and complex task execution rather than raw chat quality, with a 1M window for large corpora. *Evaluated:* no public third-party evaluation published yet. **Caveats** -- Text output only — no image generation. -- Evaluated publicly as 'Qwen3.8-Flash-Next' in third-party benchmark tables. +- Preview release with no third-party evaluations published yet, so performance is unverified outside the vendor's own numbers. +- Text input only. + +### undefined + +**minimax** · released 2026-03-18 · $0.3 in / $1.2 out per 1M tokens · 0.20M context · text in → text out + +Targeted for: **Coding, Office work, Agentic tasks** + +MiniMax model for chat, coding, office work, and agentic tasks. + +The generation before MiniMax M3: general chat plus coding and office deliverables. Cheap, but the 200K window and older agentic scores make it a fallback now that M3 and M3.1 Flash exist. + +*Evaluated:* no public third-party evaluation published yet. + +**Caveats** + +- 200K context — the smallest window in the Go catalogue. +- Superseded by MiniMax M3. ### undefined @@ -416,40 +502,6 @@ The Kimi tier built for endurance: long-horizon agent runs, web research (Browse ### undefined -**tencent** · released 2026-07-06 · $0.14 in / $0.58 out per 1M tokens · 0.26M context · text in → text out - -Targeted for: **Cheap, Reasoning, Instruction following, Tool use** - -Tencent Hy reasoning model for coding, instruction following, and agent tasks. - -A cheap reasoning model with unusually strong instruction following (IFBench) and tool use (τ-bench) for its price. Suited to spec-driven agents and short coding loops; the 256K window is the main limitation for repo-scale work. - -*Evaluated:* no public third-party evaluation published yet. - -**Caveats** - -- 256K context. -- Text input only. - -### undefined - -**deepseek** · released 2026-09-10 · $0.15 in / $0.6 out per 1M tokens · 1M context · text, image in → text out - -Targeted for: **Agentic coding, Reasoning, Cheap, High volume** - -DeepSeek's V4.1 Flash: built for reasoning and agentic coding, and the single most-used model in OpenCode by token volume. - -The default engine for long coding-agent runs. DeepSeek's own card lists Terminal-Bench, DeepSWE, CyberGym and AutomationBench scores, i.e. it is tuned for terminal work, repo-level fixes and security tasks rather than chat. With cache reads at ~0.3¢/1M it is also the cheapest way to move large volumes of agent traffic. - -*Evaluated:* no public third-party evaluation published yet. - -**Caveats** - -- Text output only. -- Price doubles during DeepSeek's peak hours (01:00–04:00 and 06:00–10:00 UTC, Mon–Fri). - -### undefined - **undisclosed** · released 2026-10-24 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 0.26M context · text in → text out Stealth model, free for a limited time @@ -460,91 +512,6 @@ _No hand-written write-up yet._ ### undefined -**openai** · released 2026-07-09 · $0.2 in / $1.2 out per 1M tokens · 1.05M context · text, image, pdf in → text out - -Targeted for: **Fast & cheap, High-volume coding, Agents** - -Cost-efficient GPT-5.6 model for fast, high-volume workloads. - -Throughput work: many small calls, classification, extraction, routing and repetitive edits where latency and cost per call decide the outcome. Keeps the GPT tool-calling behaviour at roughly twice the price of GPT-6 Luna. - -*Evaluated:* no public third-party evaluation published yet. - -**Caveats** - -- Price steps up above 272K tokens of context. - -### undefined - -**moonshotai** · released 2026-06-12 · $0.95 in / $4 out per 1M tokens · 0.26M context · text, image, video in → text out - -Targeted for: **Repo-scale coding, Long-horizon repo work, Tool use** - -Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking. - -Purpose-built for code: sustained repository work, refactors and multi-file changes where a general model wastes tokens deliberating. The tool-use (τ-bench) score is very high, so it is also good at driving MCP servers and CLI tools. Use it when the deliverable is a diff, not an essay. - -*Evaluated:* no public third-party evaluation published yet. - -**Caveats** - -- 256K context — roughly a quarter of the 1M models. -- Narrower general-purpose ability than the flagship Kimi. - -### undefined - -**xiaomi** · released 2026-04-22 · $0.14 in / $0.28 out per 1M tokens · 1M context · text, image, audio, video in → text out - -Targeted for: **Budget multimodal agents, Long context** - -Open MiMo model for multimodal coding agents and long-context automation. - -The cheapest way to get multimodal, long-context agent behaviour in Go: 14¢/28¢ per 1M. Best suited to bulk automation — many small steps over a large context — rather than to hard single-shot questions. - -*Evaluated:* no public third-party evaluation published yet. - -**Caveats** - -- Lowest tier of the MiMo line; weak on the hardest agentic benchmarks. -- Text output only. - -### undefined - -**undisclosed** · released 2026-09-23 · $0.15 in / $0.6 out per 1M tokens · 1.05M context · text, image, video in → text out - -Targeted for: **Coding, Agentic tasks, Tool use, Multimodal** - -Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input. - -An unreleased preview model with full multimodal input and tool use, priced like the value tier. It has no vendor behind it and no public evaluation, so treat it as an experiment rather than a recommendation. - -*Evaluated:* no public third-party evaluation published yet. - -**Caveats** - -- No vendor or model card — no published evaluation. -- Not listed in the live Go catalogue endpoint. - -### undefined - -**meituan** · released 2026-09-25 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 1M context · text, image in → text out - -Targeted for: **Coding, Agentic, Image understanding, Free tier** - -Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window. - -Agents that have to read a picture to act: UI automation, screenshot-to-code, chart and document understanding, then long runs of tool use against a 1M-token window. Pairs well with a free-tier workflow — long exploratory sessions without burning a paid model's allowance. - -*Evaluated:* no public third-party evaluation published yet. - -**Caveats** - -- Free for a limited time. -- Preview release: scores and behaviour may shift. -- Text output only — no image generation. - -### undefined - **zhipuai** · released 2026-06-13 · $1.4 in / $4.4 out per 1M tokens · 1M context · text in → text out Targeted for: **Long-horizon coding, Agents, Math & science** @@ -579,20 +546,20 @@ Now the value option in the MiMo line — same interface as 2.6 Pro with materia ### undefined -**minimax** · released 2026-03-18 · $0.3 in / $1.2 out per 1M tokens · 0.20M context · text in → text out +**meta** · released 2026-08-05 · $0.1 in / $0.2 out per 1M tokens · 1.05M context · text, image, video, pdf, audio in → text out -Targeted for: **Coding, Office work, Agentic tasks** +Targeted for: **Coding, Multimodal, Cheap** -MiniMax model for chat, coding, office work, and agentic tasks. +Coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows. -The generation before MiniMax M3: general chat plus coding and office deliverables. Cheap, but the 200K window and older agentic scores make it a fallback now that M3 and M3.1 Flash exist. +The previous Muse generation — kept in Go because it is cheap and coding-focused. Pick it when you want Meta's multimodal input surface at $0.10/$0.20 and 1.3 is not required; otherwise use Muse Spark 1.3. *Evaluated:* no public third-party evaluation published yet. **Caveats** -- 200K context — the smallest window in the Go catalogue. -- Superseded by MiniMax M3. +- Contributor tier — prompts and completions may be used to train future Meta models. +- Superseded by Muse Spark 1.3 on long-horizon agent tasks. ### undefined @@ -613,20 +580,73 @@ Long-context reasoning with tool calling at a modest price — useful for repo-s ### undefined -**meta** · released 2026-08-05 · $0.1 in / $0.2 out per 1M tokens · 1.05M context · text, image, video, pdf, audio in → text out +**undisclosed** · released 2026-11-03 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 1.05M context · text, image, video, pdf in → text out -Targeted for: **Coding, Multimodal, Cheap** +Stealth reasoning model with text, image, video and PDF input and tool use -Coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows. +_No hand-written write-up yet._ -The previous Muse generation — kept in Go because it is cheap and coding-focused. Pick it when you want Meta's multimodal input surface at $0.10/$0.20 and 1.3 is not required; otherwise use Muse Spark 1.3. +*Evaluated:* no public third-party evaluation published yet. + +### undefined + +**tencent** · released 2026-07-06 · $0.14 in / $0.58 out per 1M tokens · 0.26M context · text in → text out + +Targeted for: **Cheap, Reasoning, Instruction following, Tool use** + +Tencent Hy reasoning model for coding, instruction following, and agent tasks. + +A cheap reasoning model with unusually strong instruction following (IFBench) and tool use (τ-bench) for its price. Suited to spec-driven agents and short coding loops; the 256K window is the main limitation for repo-scale work. *Evaluated:* no public third-party evaluation published yet. **Caveats** -- Contributor tier — prompts and completions may be used to train future Meta models. -- Superseded by Muse Spark 1.3 on long-horizon agent tasks. +- 256K context. +- Text input only. + +### undefined + +**moonshotai** · released 2026-06-12 · $0.95 in / $4 out per 1M tokens · 0.26M context · text, image, video in → text out + +Targeted for: **Repo-scale coding, Long-horizon repo work, Tool use** + +Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking. + +Purpose-built for code: sustained repository work, refactors and multi-file changes where a general model wastes tokens deliberating. The tool-use (τ-bench) score is very high, so it is also good at driving MCP servers and CLI tools. Use it when the deliverable is a diff, not an essay. + +*Evaluated:* no public third-party evaluation published yet. + +**Caveats** + +- 256K context — roughly a quarter of the 1M models. +- Narrower general-purpose ability than the flagship Kimi. + +### undefined + +**stepfun** · released 2026-09-16 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 1M context · text, image, video in → text out + +Targeted for: **Free tier, Coding, Professional knowledge work, Multimodal** + +Free access to StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image and video input and a 1M-token context window. + +Same model as the paid Step 5 Preview, without the token bill — useful for long agent runs and multimodal work while the paid allowance is reserved for the hard tasks. + +*Evaluated:* no public third-party evaluation published yet. + +**Caveats** + +- Limited-time free entry; not present in the live Go catalogue endpoint, so availability may vary. + +### undefined + +**tencent** · released 2026-11-04 · $0.834 in / $2.501 out per 1M tokens · 1.05M context · text, image in → text out + +A next-generation multimodal productivity model with significantly enhanced Agent and complex task execution capabilities. + +_No hand-written write-up yet._ + +*Evaluated:* no public third-party evaluation published yet. ## Free models outside the Go plan diff --git a/site/assets/catalog.js b/site/assets/catalog.js index a6fb154..f653b24 100644 --- a/site/assets/catalog.js +++ b/site/assets/catalog.js @@ -2,213 +2,21 @@ // Source: models.dev/api.json (provider "opencode-go") + Artificial Analysis. export const CATALOG = [ { - "id": "qwen3.7-plus", - "n": "Qwen3.7 Plus", - "lab": "alibaba", - "released": "2026-06-02", + "id": "gpt-6-luna", + "n": "GPT-6 Luna", + "lab": "openai", + "released": "2026-09-22", "price": { - "in": 0.4, - "out": 1.6 + "in": 0.1, + "out": 0.5 }, "free": false, - "ctx": 1000000, - "modalities": "text, image, video in → text out", - "description": "Multimodal reasoning model for visual analysis, planning, and tool use", - "canonical": "alibaba/qwen3.7-plus", - "openWeights": false - }, - { - "id": "step-5-preview-free", - "n": "Step 5 Preview Free", - "lab": "stepfun", - "released": "2026-09-16", - "price": { - "in": 0, - "out": 0 - }, - "free": true, - "ctx": 1000000, - "modalities": "text, image, video in → text out", - "description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window", - "canonical": "stepfun/step-5-preview", - "openWeights": true - }, - { - "id": "hy4-preview", - "n": "Hy4 preview", - "lab": "tencent", - "released": "2026-08-28", - "price": { - "in": 0.834, - "out": 2.501 - }, - "free": false, - "ctx": 1024000, - "modalities": "text in → text out", - "description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.", - "canonical": "tencent/hy4-preview", - "openWeights": true - }, - { - "id": "cat-jam-free", - "n": "Cat Jam Free", - "lab": "", - "released": "2026-10-12", - "price": { - "in": 0, - "out": 0 - }, - "free": true, - "ctx": 1048576, - "modalities": "text in → text out", - "description": "A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.", - "canonical": null, - "openWeights": false - }, - { - "id": "gemini-4-argon", - "n": "Gemini 4 Argon", - "lab": "google", - "released": "2026-10-13", - "price": { - "in": 2, - "out": 10 - }, - "free": false, - "ctx": 1048576, - "modalities": "text, image, video, audio, pdf in → text out", - "description": "Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents", - "canonical": "google/gemini-4-argon", - "openWeights": false - }, - { - "id": "beam-free", - "n": "Beam Free", - "lab": "reflection", - "released": "2026-10-05", - "price": { - "in": 0, - "out": 0 - }, - "free": true, - "ctx": 1048576, - "modalities": "text in → text out", - "description": "Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows", - "canonical": "reflection/beam-1.0-501b-a23b", - "openWeights": true - }, - { - "id": "grok-4.7", - "n": "Grok 4.7", - "lab": "xai", - "released": "2026-09-21", - "price": { - "in": 2, - "out": 6 - }, - "free": false, - "ctx": 500000, + "ctx": 1050000, "modalities": "text, image, pdf in → text out", - "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", - "canonical": "xai/grok-4.7", + "description": "OpenAI's most efficient model for focused, high-volume tasks", + "canonical": "openai/gpt-6-luna", "openWeights": false }, - { - "id": "minimax-m3.1-flash-free", - "n": "MiniMax M3.1 Flash Free", - "lab": "minimax", - "released": "2026-10-19", - "price": { - "in": 0, - "out": 0 - }, - "free": true, - "ctx": 1000000, - "modalities": "text, image, video in → text out", - "description": "Frontier multimodal coding model with 1M context window and tunable thinking depth", - "canonical": "minimax/MiniMax-M3.1-Flash", - "openWeights": false - }, - { - "id": "qwen3.8-flash", - "n": "Qwen3.8 Flash", - "lab": "alibaba", - "released": "2026-08-26", - "price": { - "in": 0.15, - "out": 0.47 - }, - "free": false, - "ctx": 1000000, - "modalities": "text, image, video in → text out", - "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", - "canonical": "alibaba/qwen3.8-flash", - "openWeights": false - }, - { - "id": "step-5-preview", - "n": "Step 5 Preview", - "lab": "stepfun", - "released": "2026-09-16", - "price": { - "in": 1, - "out": 2.7 - }, - "free": false, - "ctx": 1000000, - "modalities": "text, image, video in → text out", - "description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window", - "canonical": "stepfun/step-5-preview", - "openWeights": true - }, - { - "id": "kimi-k3.1-pro", - "n": "Kimi K3.1 Pro", - "lab": "moonshotai", - "released": "2026-10-23", - "price": { - "in": 2, - "out": 10 - }, - "free": false, - "ctx": 1048576, - "modalities": "text, image, video in → text out", - "description": "Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work", - "canonical": "moonshotai/kimi-k3.1-pro", - "openWeights": false - }, - { - "id": "kimi-k3", - "n": "Kimi K3", - "lab": "moonshotai", - "released": "2026-07-16", - "price": { - "in": 3, - "out": 15 - }, - "free": false, - "ctx": 1048576, - "modalities": "text, image, video in → text out", - "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", - "canonical": "moonshotai/kimi-k3", - "openWeights": true - }, - { - "id": "hy3", - "n": "Hy3", - "lab": "tencent", - "released": "2026-07-06", - "price": { - "in": 0.14, - "out": 0.58 - }, - "free": false, - "ctx": 256000, - "modalities": "text in → text out", - "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", - "canonical": "tencent/hy3", - "openWeights": true - }, { "id": "deepseek-v4.1-flash", "n": "DeepSeek V4.1 Flash", @@ -226,131 +34,51 @@ export const CATALOG = [ "openWeights": true }, { - "id": "deepseek-v4-pro", - "n": "DeepSeek V4 Pro (New)", - "lab": "deepseek", - "released": "2026-04-24", - "price": { - "in": 0.66, - "out": 1.98 - }, - "free": false, - "ctx": 1000000, - "modalities": "text in → text out", - "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", - "canonical": "deepseek/deepseek-v4-pro", - "openWeights": true - }, - { - "id": "gemini-4-argon-contributor", - "n": "Gemini 4 Argon Contributor", - "lab": "google", - "released": "2026-10-13", - "price": { - "in": 4, - "out": 20 - }, - "free": false, - "ctx": 1048576, - "modalities": "text, image, video, audio, pdf in → text out", - "description": "Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents", - "canonical": "google/gemini-4-argon", - "openWeights": false - }, - { - "id": "mimo-v2.6-flash", - "n": "MiMo-V2.6-Flash", - "lab": "xiaomi", - "released": "2026-09-22", - "price": { - "in": 0.14, - "out": 0.28 - }, - "free": false, - "ctx": 1048576, - "modalities": "text, image, audio, video in → text out", - "description": "MiMo Flash model for multimodal coding agents and long-context automation", - "canonical": "xiaomi/mimo-v2.6-flash", - "openWeights": true - }, - { - "id": "iceman-contributor-free", - "n": "Iceman Contributor Free", - "lab": "", - "released": "2026-10-24", - "price": { - "in": 0, - "out": 0 - }, - "free": true, - "ctx": 262144, - "modalities": "text in → text out", - "description": "Stealth model, free for a limited time", - "canonical": null, - "openWeights": false - }, - { - "id": "gpt-5.6-luna", - "n": "GPT-5.6 Luna", - "lab": "openai", - "released": "2026-07-09", - "price": { - "in": 0.2, - "out": 1.2 - }, - "free": false, - "ctx": 1050000, - "modalities": "text, image, pdf in → text out", - "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", - "canonical": "openai/gpt-5.6-luna", - "openWeights": false - }, - { - "id": "kimi-k2.7-code", - "n": "Kimi K2.7 Code", - "lab": "moonshotai", - "released": "2026-06-12", - "price": { - "in": 0.95, - "out": 4 - }, - "free": false, - "ctx": 262144, - "modalities": "text, image, video in → text out", - "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", - "canonical": "moonshotai/kimi-k2.7-code", - "openWeights": true - }, - { - "id": "mimo-v2.5", - "n": "MiMo V2.5", - "lab": "xiaomi", - "released": "2026-04-22", - "price": { - "in": 0.14, - "out": 0.28 - }, - "free": false, - "ctx": 1000000, - "modalities": "text, image, audio, video in → text out", - "description": "MiMo omni model for text, image, video, audio, and agents", - "canonical": "xiaomi/mimo-v2.5", - "openWeights": true - }, - { - "id": "space-bunny", - "n": "Space Bunny", - "lab": "", - "released": "2026-09-23", + "id": "qwen3.8-flash", + "n": "Qwen3.8 Flash", + "lab": "alibaba", + "released": "2026-08-26", "price": { "in": 0.15, - "out": 0.6 + "out": 0.47 + }, + "free": false, + "ctx": 1000000, + "modalities": "text, image, video in → text out", + "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", + "canonical": "alibaba/qwen3.8-flash", + "openWeights": false + }, + { + "id": "claude-haiku-5-5", + "n": "Claude Haiku 5.5", + "lab": "anthropic", + "released": "2026-10-07", + "price": { + "in": 0.1, + "out": 0.5 + }, + "free": false, + "ctx": 1000000, + "modalities": "text, image, pdf in → text out", + "description": "Fast Claude model for responsive assistance, classification, and lightweight agents", + "canonical": "anthropic/claude-haiku-5-5", + "openWeights": false + }, + { + "id": "muse-spark-1.3-contributor", + "n": "Muse Spark 1.3 Contributor", + "lab": "meta", + "released": "2026-09-02", + "price": { + "in": 0.1, + "out": 0.2 }, "free": false, "ctx": 1048576, - "modalities": "text, image, video in → text out", - "description": "Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input", - "canonical": null, + "modalities": "text, image, video, pdf, audio in → text out", + "description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.", + "canonical": "meta/muse-spark-1.3", "openWeights": false }, { @@ -370,51 +98,35 @@ export const CATALOG = [ "openWeights": false }, { - "id": "glm-5.2", - "n": "GLM-5.2", - "lab": "zhipuai", - "released": "2026-06-13", + "id": "gemini-4-argon-contributor", + "n": "Gemini 4 Argon Contributor", + "lab": "google", + "released": "2026-10-13", "price": { - "in": 1.4, - "out": 4.4 + "in": 4, + "out": 20 }, "free": false, - "ctx": 1000000, - "modalities": "text in → text out", - "description": "Open flagship GLM for long-horizon coding agents and million-token context work", - "canonical": "zhipuai/glm-5.2", - "openWeights": true + "ctx": 1048576, + "modalities": "text, image, video, audio, pdf in → text out", + "description": "Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents", + "canonical": "google/gemini-4-argon", + "openWeights": false }, { - "id": "glm-5.3-flash", - "n": "GLM-5.3-Flash", - "lab": "zhipuai", - "released": "2026-08-26", + "id": "qwen3.7-plus", + "n": "Qwen3.7 Plus", + "lab": "alibaba", + "released": "2026-06-02", "price": { - "in": 0.15, - "out": 0.5 + "in": 0.4, + "out": 1.6 }, "free": false, "ctx": 1000000, "modalities": "text, image, video in → text out", - "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", - "canonical": "zhipuai/glm-5.3-flash", - "openWeights": true - }, - { - "id": "gpt-6-luna", - "n": "GPT-6 Luna", - "lab": "openai", - "released": "2026-09-22", - "price": { - "in": 0.1, - "out": 0.5 - }, - "free": false, - "ctx": 1050000, - "modalities": "text, image, pdf in → text out", - "description": "OpenAI's most efficient model for focused, high-volume tasks", - "canonical": "openai/gpt-6-luna", + "description": "Multimodal reasoning model for visual analysis, planning, and tool use", + "canonical": "alibaba/qwen3.7-plus", "openWeights": false }, { @@ -434,53 +146,101 @@ export const CATALOG = [ "openWeights": true }, { - "id": "qwen3.8-max", - "n": "Qwen3.8 Max", - "lab": "alibaba", - "released": "2026-08-03", - "price": { - "in": 2, - "out": 6 - }, - "free": false, - "ctx": 1000000, - "modalities": "text, image, video in → text out", - "description": "2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows", - "canonical": "alibaba/qwen3.8-max", - "openWeights": false - }, - { - "id": "mimo-v2.5-pro", - "n": "MiMo V2.5 Pro", + "id": "mimo-v2.6-flash", + "n": "MiMo-V2.6-Flash", "lab": "xiaomi", - "released": "2026-04-22", + "released": "2026-09-22", "price": { - "in": 0.435, - "out": 0.87 + "in": 0.14, + "out": 0.28 }, "free": false, "ctx": 1048576, - "modalities": "text in → text out", - "description": "MiMo pro model for strong multimodal reasoning and agent execution", - "canonical": "xiaomi/mimo-v2.5-pro", + "modalities": "text, image, audio, video in → text out", + "description": "MiMo Flash model for multimodal coding agents and long-context automation", + "canonical": "xiaomi/mimo-v2.6-flash", "openWeights": true }, { - "id": "claude-haiku-5-5", - "n": "Claude Haiku 5.5", - "lab": "anthropic", - "released": "2026-10-07", + "id": "beam-free", + "n": "Beam Free", + "lab": "reflection", + "released": "2026-10-05", "price": { - "in": 0.1, - "out": 0.5 + "in": 0, + "out": 0 + }, + "free": true, + "ctx": 1048576, + "modalities": "text in → text out", + "description": "Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows", + "canonical": "reflection/beam-1.0-501b-a23b", + "openWeights": true + }, + { + "id": "space-bunny", + "n": "Space Bunny", + "lab": "", + "released": "2026-09-23", + "price": { + "in": 0.15, + "out": 0.6 + }, + "free": false, + "ctx": 1048576, + "modalities": "text, image, video in → text out", + "description": "Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input", + "canonical": null, + "openWeights": false + }, + { + "id": "mimo-v2.5", + "n": "MiMo V2.5", + "lab": "xiaomi", + "released": "2026-04-22", + "price": { + "in": 0.14, + "out": 0.28 }, "free": false, "ctx": 1000000, - "modalities": "text, image, pdf in → text out", - "description": "Fast Claude model for responsive assistance, classification, and lightweight agents", - "canonical": "anthropic/claude-haiku-5-5", + "modalities": "text, image, audio, video in → text out", + "description": "MiMo omni model for text, image, video, audio, and agents", + "canonical": "xiaomi/mimo-v2.5", + "openWeights": true + }, + { + "id": "cat-jam-free", + "n": "Cat Jam Free", + "lab": "", + "released": "2026-10-12", + "price": { + "in": 0, + "out": 0 + }, + "free": true, + "ctx": 1048576, + "modalities": "text in → text out", + "description": "A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.", + "canonical": null, "openWeights": false }, + { + "id": "hy4-preview", + "n": "Hy4 preview", + "lab": "tencent", + "released": "2026-08-28", + "price": { + "in": 0.834, + "out": 2.501 + }, + "free": false, + "ctx": 1024000, + "modalities": "text in → text out", + "description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.", + "canonical": "tencent/hy4-preview", + "openWeights": true + }, { "id": "minimax-m2.7", "n": "MiniMax-M2.7", @@ -498,37 +258,101 @@ export const CATALOG = [ "openWeights": true }, { - "id": "longcat-2.0", - "n": "LongCat-2.0", - "lab": "meituan", - "released": "2026-06-30", + "id": "kimi-k3", + "n": "Kimi K3", + "lab": "moonshotai", + "released": "2026-07-16", "price": { - "in": 0.3, - "out": 1.2 + "in": 3, + "out": 15 }, "free": false, - "ctx": 1000000, - "modalities": "text in → text out", - "description": "Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window", - "canonical": "meituan/longcat-2.0", + "ctx": 1048576, + "modalities": "text, image, video in → text out", + "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", + "canonical": "moonshotai/kimi-k3", "openWeights": true }, { - "id": "minimax-m3", - "n": "MiniMax-M3", - "lab": "minimax", - "released": "2026-06-01", + "id": "glm-5.3-flash", + "n": "GLM-5.3-Flash", + "lab": "zhipuai", + "released": "2026-08-26", "price": { - "in": 0.3, - "out": 1.2 + "in": 0.15, + "out": 0.5 }, "free": false, "ctx": 1000000, "modalities": "text, image, video in → text out", - "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", - "canonical": "minimax/MiniMax-M3", + "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", + "canonical": "zhipuai/glm-5.3-flash", "openWeights": true }, + { + "id": "iceman-contributor-free", + "n": "Iceman Contributor Free", + "lab": "", + "released": "2026-10-24", + "price": { + "in": 0, + "out": 0 + }, + "free": true, + "ctx": 262144, + "modalities": "text in → text out", + "description": "Stealth model, free for a limited time", + "canonical": null, + "openWeights": false + }, + { + "id": "glm-5.2", + "n": "GLM-5.2", + "lab": "zhipuai", + "released": "2026-06-13", + "price": { + "in": 1.4, + "out": 4.4 + }, + "free": false, + "ctx": 1000000, + "modalities": "text in → text out", + "description": "Open flagship GLM for long-horizon coding agents and million-token context work", + "canonical": "zhipuai/glm-5.2", + "openWeights": true + }, + { + "id": "mimo-v2.5-pro", + "n": "MiMo V2.5 Pro", + "lab": "xiaomi", + "released": "2026-04-22", + "price": { + "in": 0.435, + "out": 0.87 + }, + "free": false, + "ctx": 1048576, + "modalities": "text in → text out", + "description": "MiMo pro model for strong multimodal reasoning and agent execution", + "canonical": "xiaomi/mimo-v2.5-pro", + "openWeights": true + }, + { + "id": "qwen3.8-max", + "n": "Qwen3.8 Max", + "lab": "alibaba", + "released": "2026-08-03", + "price": { + "in": 2, + "out": 6 + }, + "free": false, + "ctx": 1000000, + "modalities": "text, image, video in → text out", + "description": "2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows", + "canonical": "alibaba/qwen3.8-max", + "openWeights": false + }, { "id": "mimo-v2.6-pro", "n": "MiMo-V2.6-Pro", @@ -546,21 +370,37 @@ export const CATALOG = [ "openWeights": true }, { - "id": "muse-spark-1.3-contributor", - "n": "Muse Spark 1.3 Contributor", - "lab": "meta", - "released": "2026-09-02", + "id": "gemini-4-argon", + "n": "Gemini 4 Argon", + "lab": "google", + "released": "2026-10-13", "price": { - "in": 0.1, - "out": 0.2 + "in": 2, + "out": 10 }, "free": false, "ctx": 1048576, - "modalities": "text, image, video, pdf, audio in → text out", - "description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.", - "canonical": "meta/muse-spark-1.3", + "modalities": "text, image, video, audio, pdf in → text out", + "description": "Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents", + "canonical": "google/gemini-4-argon", "openWeights": false }, + { + "id": "minimax-m3.1-flash", + "n": "MiniMax M3.1 Flash", + "lab": "minimax", + "released": "2026-10-19", + "price": { + "in": 0.15, + "out": 0.6 + }, + "free": false, + "ctx": 1000000, + "modalities": "text, image, video in → text out", + "description": "Frontier multimodal coding model with 1M context window and tunable thinking depth", + "canonical": "minimax/MiniMax-M3.1-Flash", + "openWeights": true + }, { "id": "muse-spark-1.2-contributor", "n": "Muse Spark 1.2 Contributor", @@ -578,147 +418,288 @@ export const CATALOG = [ "openWeights": false }, { - "id": "minimax-m3.1-flash", - "n": "MiniMax M3.1 Flash", - "lab": "minimax", - "released": "2026-10-19", + "id": "longcat-2.0", + "n": "LongCat-2.0", + "lab": "meituan", + "released": "2026-06-30", "price": { - "in": 0.15, - "out": 0.6 + "in": 0.3, + "out": 1.2 + }, + "free": false, + "ctx": 1000000, + "modalities": "text in → text out", + "description": "Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window", + "canonical": "meituan/longcat-2.0", + "openWeights": true + }, + { + "id": "grok-4.7", + "n": "Grok 4.7", + "lab": "xai", + "released": "2026-09-21", + "price": { + "in": 2, + "out": 6 + }, + "free": false, + "ctx": 500000, + "modalities": "text, image, pdf in → text out", + "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", + "canonical": "xai/grok-4.7", + "openWeights": false + }, + { + "id": "crouton-alpha-free", + "n": "Crouton Alpha Free", + "lab": "", + "released": "2026-11-03", + "price": { + "in": 0, + "out": 0 + }, + "free": true, + "ctx": 1048576, + "modalities": "text, image, video, pdf in → text out", + "description": "Stealth reasoning model with text, image, video and PDF input and tool use", + "canonical": null, + "openWeights": false + }, + { + "id": "hy3", + "n": "Hy3", + "lab": "tencent", + "released": "2026-07-06", + "price": { + "in": 0.14, + "out": 0.58 + }, + "free": false, + "ctx": 256000, + "modalities": "text in → text out", + "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", + "canonical": "tencent/hy3", + "openWeights": true + }, + { + "id": "kimi-k2.7-code", + "n": "Kimi K2.7 Code", + "lab": "moonshotai", + "released": "2026-06-12", + "price": { + "in": 0.95, + "out": 4 + }, + "free": false, + "ctx": 262144, + "modalities": "text, image, video in → text out", + "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", + "canonical": "moonshotai/kimi-k2.7-code", + "openWeights": true + }, + { + "id": "step-5-preview-free", + "n": "Step 5 Preview Free", + "lab": "stepfun", + "released": "2026-09-16", + "price": { + "in": 0, + "out": 0 + }, + "free": true, + "ctx": 1000000, + "modalities": "text, image, video in → text out", + "description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window", + "canonical": "stepfun/step-5-preview", + "openWeights": true + }, + { + "id": "step-5-preview", + "n": "Step 5 Preview", + "lab": "stepfun", + "released": "2026-09-16", + "price": { + "in": 1, + "out": 2.7 }, "free": false, "ctx": 1000000, "modalities": "text, image, video in → text out", + "description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window", + "canonical": "stepfun/step-5-preview", + "openWeights": true + }, + { + "id": "gpt-5.6-luna", + "n": "GPT-5.6 Luna", + "lab": "openai", + "released": "2026-07-09", + "price": { + "in": 0.2, + "out": 1.2 + }, + "free": false, + "ctx": 1050000, + "modalities": "text, image, pdf in → text out", + "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", + "canonical": "openai/gpt-5.6-luna", + "openWeights": false + }, + { + "id": "kimi-k3.1-pro", + "n": "Kimi K3.1 Pro", + "lab": "moonshotai", + "released": "2026-10-23", + "price": { + "in": 2, + "out": 10 + }, + "free": false, + "ctx": 1048576, + "modalities": "text, image, video in → text out", + "description": "Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work", + "canonical": "moonshotai/kimi-k3.1-pro", + "openWeights": true + }, + { + "id": "minimax-m3.1-flash-free", + "n": "MiniMax M3.1 Flash Free", + "lab": "minimax", + "released": "2026-10-19", + "price": { + "in": 0, + "out": 0 + }, + "free": true, + "ctx": 1000000, + "modalities": "text, image, video in → text out", "description": "Frontier multimodal coding model with 1M context window and tunable thinking depth", "canonical": "minimax/MiniMax-M3.1-Flash", + "openWeights": true + }, + { + "id": "deepseek-v4-pro", + "n": "DeepSeek V4 Pro", + "lab": "deepseek", + "released": "2026-04-24", + "price": { + "in": 0.66, + "out": 1.98 + }, + "free": false, + "ctx": 1000000, + "modalities": "text in → text out", + "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", + "canonical": "deepseek/deepseek-v4-pro", + "openWeights": true + }, + { + "id": "hy4", + "n": "Hy4", + "lab": "tencent", + "released": "2026-11-04", + "price": { + "in": 0.834, + "out": 2.501 + }, + "free": false, + "ctx": 1048576, + "modalities": "text, image in → text out", + "description": "A next-generation multimodal productivity model with significantly enhanced Agent and complex task execution capabilities.", + "canonical": "tencent/hy4", "openWeights": false + }, + { + "id": "minimax-m3", + "n": "MiniMax-M3", + "lab": "minimax", + "released": "2026-06-01", + "price": { + "in": 0.3, + "out": 1.2 + }, + "free": false, + "ctx": 1000000, + "modalities": "text, image, video in → text out", + "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", + "canonical": "minimax/MiniMax-M3", + "openWeights": true } ]; export const SNAPSHOT = { - "generated": "2026-11-02T05:24:13.718Z", - "models": 37, - "newModels": [], + "generated": "2026-11-09T05:24:25.577Z", + "models": 39, + "newModels": [ + "crouton-alpha-free", + "hy4" + ], "removedModels": [], "deltas": [ - { - "id": "mimo-v2.6-pro", - "from": 46.3, - "to": 29.9, - "delta": -16.4 - }, - { - "id": "step-5-preview", - "from": 43.7, - "to": 28.5, - "delta": -15.2 - }, - { - "id": "glm-5.3-flash", - "from": 41.8, - "to": 27.8, - "delta": -14 - }, - { - "id": "minimax-m3.1-flash-free", - "from": 42.7, - "to": 28.9, - "delta": -13.8 - }, - { - "id": "minimax-m3.1-flash", - "from": 42.7, - "to": 28.9, - "delta": -13.8 - }, - { - "id": "glm-5.3", - "from": 44.8, - "to": 31.7, - "delta": -13.1 - }, - { - "id": "deepseek-v4-pro", - "from": 36, - "to": 23.1, - "delta": -12.9 - }, - { - "id": "beam-free", - "from": 30.3, - "to": 17.7, - "delta": -12.6 - }, { "id": "grok-4.7", - "from": 46.4, - "to": 34.3, - "delta": -12.1 - }, - { - "id": "qwen3.8-max", - "from": 45.4, - "to": 33.6, - "delta": -11.8 - }, - { - "id": "muse-spark-1.3-contributor", - "from": 48.1, - "to": 36.4, - "delta": -11.7 - }, - { - "id": "mimo-v2.6-flash", - "from": 37.9, - "to": 26.7, - "delta": -11.2 - }, - { - "id": "minimax-m3", - "from": 29.2, - "to": 18.7, - "delta": -10.5 - }, - { - "id": "gpt-6-luna", - "from": 38.1, - "to": 27.8, - "delta": -10.3 + "from": 34.3, + "to": 35.5, + "delta": 1.2 }, { "id": "kimi-k3.1-pro", - "from": 55.1, - "to": 46, - "delta": -9.1 + "from": 46, + "to": 46.5, + "delta": 0.5 }, { "id": "claude-haiku-5-5", - "from": 43.4, - "to": 36.2, - "delta": -7.2 + "from": 36.2, + "to": 36.5, + "delta": 0.3 }, { - "id": "gemini-4-argon", - "from": 52.6, - "to": 50.4, - "delta": -2.2 + "id": "muse-spark-1.3-contributor", + "from": 36.4, + "to": 36.6, + "delta": 0.2 }, { - "id": "gemini-4-argon-contributor", - "from": 52.6, - "to": 50.4, - "delta": -2.2 + "id": "minimax-m3.1-flash", + "from": 28.9, + "to": 29.1, + "delta": 0.2 + }, + { + "id": "minimax-m3.1-flash-free", + "from": 28.9, + "to": 29.1, + "delta": 0.2 + }, + { + "id": "minimax-m3", + "from": 18.7, + "to": 18.9, + "delta": 0.2 + }, + { + "id": "gpt-6-luna", + "from": 27.8, + "to": 27.9, + "delta": 0.1 + }, + { + "id": "qwen3.8-max", + "from": 33.6, + "to": 33.7, + "delta": 0.1 } ], "notInLiveCatalog": [ - "step-5-preview-free", - "cat-jam-free", - "minimax-m3.1-flash-free", - "gemini-4-argon-contributor", - "mimo-v2.5", - "space-bunny", "longcat-2.5-preview-free", + "gemini-4-argon-contributor", + "space-bunny", + "mimo-v2.5", + "cat-jam-free", + "minimax-m2.7", "mimo-v2.5-pro", - "minimax-m2.7" + "step-5-preview-free", + "minimax-m3.1-flash-free" ] }; diff --git a/site/assets/evals.js b/site/assets/evals.js index f86aa38..24ad0b4 100644 --- a/site/assets/evals.js +++ b/site/assets/evals.js @@ -2,12 +2,40 @@ // Benchmark scores from Artificial Analysis (single consistent harness), scaled to 0-100. export const RAW = [ { - "id": "qwen3.7-plus", - "n": "Qwen3.7 Plus", - "lab": "alibaba", + "id": "gpt-6-luna", + "n": "GPT-6 Luna", + "lab": "openai", "free": false, - "pi": 0.4, - "po": 1.6, + "pi": 0.1, + "po": 0.5, + "ii": 27.9, + "fc": 41.9, + "scicode": 54.6, + "tb21": null, + "tb40": 12.6, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": 43.8, + "auto": 53.2, + "gpqa": null, + "critpt": 19.4, + "hle": 38.5, + "lcr": 83.3, + "ifbench": null, + "mmmu": 79.7, + "gdpv": null, + "gdppdf": 22.8, + "ctx": 1050000 + }, + { + "id": "deepseek-v4.1-flash", + "n": "DeepSeek V4.1 Flash", + "lab": "deepseek", + "free": false, + "pi": 0.15, + "po": 0.6, "ii": null, "fc": null, "scicode": null, @@ -29,202 +57,6 @@ export const RAW = [ "gdppdf": null, "ctx": 1000000 }, - { - "id": "step-5-preview-free", - "n": "Step 5 Preview Free", - "lab": "stepfun", - "free": true, - "pi": 0, - "po": 0, - "ii": null, - "fc": null, - "scicode": null, - "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 1000000 - }, - { - "id": "hy4-preview", - "n": "Hy4 preview", - "lab": "tencent", - "free": false, - "pi": 0.834, - "po": 2.501, - "ii": null, - "fc": null, - "scicode": null, - "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 1024000 - }, - { - "id": "cat-jam-free", - "n": "Cat Jam Free", - "lab": "", - "free": true, - "pi": 0, - "po": 0, - "ii": null, - "fc": null, - "scicode": null, - "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 1048576 - }, - { - "id": "gemini-4-argon", - "n": "Gemini 4 Argon", - "lab": "google", - "free": false, - "pi": 2, - "po": 10, - "ii": 50.4, - "fc": 43.5, - "scicode": 61.8, - "tb21": null, - "tb40": 57.1, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": 48.8, - "auto": 77.5, - "gpqa": null, - "critpt": 27.1, - "hle": 57.1, - "lcr": 79.7, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": 21.8, - "ctx": 1048576 - }, - { - "id": "beam-free", - "n": "Beam Free", - "lab": "reflection", - "free": true, - "pi": 0, - "po": 0, - "ii": 17.7, - "fc": 24.3, - "scicode": 48.5, - "tb21": null, - "tb40": 3, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": 48.5, - "gpqa": null, - "critpt": 13.1, - "hle": 34.7, - "lcr": 78, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": 11.6, - "ctx": 1048576 - }, - { - "id": "grok-4.7", - "n": "Grok 4.7", - "lab": "xai", - "free": false, - "pi": 2, - "po": 6, - "ii": 34.3, - "fc": 33.8, - "scicode": 57.4, - "tb21": null, - "tb40": 25.8, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": 52.5, - "auto": 65.6, - "gpqa": null, - "critpt": 17.7, - "hle": 43.1, - "lcr": 76.7, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": 20, - "ctx": 500000 - }, - { - "id": "minimax-m3.1-flash-free", - "n": "MiniMax M3.1 Flash Free", - "lab": "minimax", - "free": true, - "pi": 0, - "po": 0, - "ii": 28.9, - "fc": 38.6, - "scicode": 53.4, - "tb21": null, - "tb40": 25.8, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": 72.5, - "gpqa": null, - "critpt": 22.3, - "hle": 48, - "lcr": 79.7, - "ifbench": null, - "mmmu": 79.1, - "gdpv": null, - "gdppdf": 20.8, - "ctx": 1000000 - }, { "id": "qwen3.8-flash", "n": "Qwen3.8 Flash", @@ -254,61 +86,369 @@ export const RAW = [ "ctx": 1000000 }, { - "id": "step-5-preview", - "n": "Step 5 Preview", - "lab": "stepfun", + "id": "claude-haiku-5-5", + "n": "Claude Haiku 5.5", + "lab": "anthropic", "free": false, - "pi": 1, - "po": 2.7, - "ii": 28.5, - "fc": 38.4, - "scicode": 58.9, + "pi": 0.1, + "po": 0.5, + "ii": 36.5, + "fc": 41.8, + "scicode": 55, "tb21": null, - "tb40": 33.3, - "tbh": null, - "tau2": null, - "taub": null, - "apex": 38, - "analyst": 35, - "auto": 51, - "gpqa": null, - "critpt": 20.9, - "hle": 46.5, - "lcr": 88.3, - "ifbench": null, - "mmmu": 76.4, - "gdpv": null, - "gdppdf": 14.8, - "ctx": 1000000 - }, - { - "id": "kimi-k3.1-pro", - "n": "Kimi K3.1 Pro", - "lab": "moonshotai", - "free": false, - "pi": 2, - "po": 10, - "ii": 46, - "fc": 47.1, - "scicode": 60.8, - "tb21": null, - "tb40": 67.2, + "tb40": 32.8, "tbh": null, "tau2": null, "taub": null, "apex": null, - "analyst": 38.8, - "auto": 73.3, + "analyst": 53.8, + "auto": 35.4, "gpqa": null, - "critpt": 24.6, - "hle": 52.5, - "lcr": 86.3, + "critpt": 18.9, + "hle": 44.4, + "lcr": 82.7, "ifbench": null, - "mmmu": 83.9, + "mmmu": null, "gdpv": null, - "gdppdf": 31.4, + "gdppdf": 20.8, + "ctx": 1000000 + }, + { + "id": "muse-spark-1.3-contributor", + "n": "Muse Spark 1.3 Contributor", + "lab": "meta", + "free": false, + "pi": 0.1, + "po": 0.2, + "ii": 36.6, + "fc": 40.6, + "scicode": 58.8, + "tb21": 84.3, + "tb40": 33.3, + "tbh": null, + "tau2": null, + "taub": 50.5, + "apex": null, + "analyst": 37.5, + "auto": 57.9, + "gpqa": 93.5, + "critpt": 24.9, + "hle": 48.7, + "lcr": 83, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": 26.6, "ctx": 1048576 }, + { + "id": "longcat-2.5-preview-free", + "n": "LongCat 2.5 Preview Free", + "lab": "meituan", + "free": true, + "pi": 0, + "po": 0, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1000000 + }, + { + "id": "gemini-4-argon-contributor", + "n": "Gemini 4 Argon Contributor", + "lab": "google", + "free": false, + "pi": 4, + "po": 20, + "ii": 50.4, + "fc": 43.5, + "scicode": 61.8, + "tb21": null, + "tb40": 57.1, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": 48.8, + "auto": 77.5, + "gpqa": null, + "critpt": 27.1, + "hle": 57.1, + "lcr": 79.7, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": 21.8, + "ctx": 1048576 + }, + { + "id": "qwen3.7-plus", + "n": "Qwen3.7 Plus", + "lab": "alibaba", + "free": false, + "pi": 0.4, + "po": 1.6, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1000000 + }, + { + "id": "glm-5.3", + "n": "GLM-5.3", + "lab": "zhipuai", + "free": false, + "pi": 1.4, + "po": 4.4, + "ii": 31.7, + "fc": 40.1, + "scicode": 59, + "tb21": 83.9, + "tb40": 41.9, + "tbh": null, + "tau2": null, + "taub": 50.3, + "apex": null, + "analyst": 38.8, + "auto": 62.2, + "gpqa": 91.7, + "critpt": 19.1, + "hle": 42.3, + "lcr": 79.7, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": 11.2, + "ctx": 1000000 + }, + { + "id": "mimo-v2.6-flash", + "n": "MiMo-V2.6-Flash", + "lab": "xiaomi", + "free": false, + "pi": 0.14, + "po": 0.28, + "ii": 26.7, + "fc": 42.1, + "scicode": 51.3, + "tb21": null, + "tb40": 22.7, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": 64.1, + "gpqa": null, + "critpt": 12, + "hle": 35.1, + "lcr": 74.3, + "ifbench": null, + "mmmu": 73.1, + "gdpv": null, + "gdppdf": 9, + "ctx": 1048576 + }, + { + "id": "beam-free", + "n": "Beam Free", + "lab": "reflection", + "free": true, + "pi": 0, + "po": 0, + "ii": 17.7, + "fc": 24.3, + "scicode": 48.5, + "tb21": null, + "tb40": 3, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": 48.5, + "gpqa": null, + "critpt": 13.1, + "hle": 34.7, + "lcr": 78, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": 11.6, + "ctx": 1048576 + }, + { + "id": "space-bunny", + "n": "Space Bunny", + "lab": "", + "free": false, + "pi": 0.15, + "po": 0.6, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1048576 + }, + { + "id": "mimo-v2.5", + "n": "MiMo V2.5", + "lab": "xiaomi", + "free": false, + "pi": 0.14, + "po": 0.28, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1000000 + }, + { + "id": "cat-jam-free", + "n": "Cat Jam Free", + "lab": "", + "free": true, + "pi": 0, + "po": 0, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1048576 + }, + { + "id": "hy4-preview", + "n": "Hy4 preview", + "lab": "tencent", + "free": false, + "pi": 0.834, + "po": 2.501, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1024000 + }, + { + "id": "minimax-m2.7", + "n": "MiniMax-M2.7", + "lab": "minimax", + "free": false, + "pi": 0.3, + "po": 1.2, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 204800 + }, { "id": "kimi-k3", "n": "Kimi K3", @@ -337,6 +477,342 @@ export const RAW = [ "gdppdf": null, "ctx": 1048576 }, + { + "id": "glm-5.3-flash", + "n": "GLM-5.3-Flash", + "lab": "zhipuai", + "free": false, + "pi": 0.15, + "po": 0.5, + "ii": 27.8, + "fc": 41, + "scicode": 51.6, + "tb21": 84.3, + "tb40": 32.8, + "tbh": null, + "tau2": null, + "taub": 47.2, + "apex": null, + "analyst": 25, + "auto": 60.4, + "gpqa": 91.2, + "critpt": 15.4, + "hle": 39.9, + "lcr": 80, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": 15.4, + "ctx": 1000000 + }, + { + "id": "iceman-contributor-free", + "n": "Iceman Contributor Free", + "lab": "", + "free": true, + "pi": 0, + "po": 0, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 262144 + }, + { + "id": "glm-5.2", + "n": "GLM-5.2", + "lab": "zhipuai", + "free": false, + "pi": 1.4, + "po": 4.4, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1000000 + }, + { + "id": "mimo-v2.5-pro", + "n": "MiMo V2.5 Pro", + "lab": "xiaomi", + "free": false, + "pi": 0.435, + "po": 0.87, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1048576 + }, + { + "id": "qwen3.8-max", + "n": "Qwen3.8 Max", + "lab": "alibaba", + "free": false, + "pi": 2, + "po": 6, + "ii": 33.7, + "fc": 43.2, + "scicode": 52.1, + "tb21": 88.8, + "tb40": 38.9, + "tbh": null, + "tau2": null, + "taub": 47.8, + "apex": 42.4, + "analyst": 45, + "auto": 56.2, + "gpqa": 92.8, + "critpt": 17.7, + "hle": 43.1, + "lcr": 80.3, + "ifbench": null, + "mmmu": 82.8, + "gdpv": null, + "gdppdf": 22.8, + "ctx": 1000000 + }, + { + "id": "mimo-v2.6-pro", + "n": "MiMo-V2.6-Pro", + "lab": "xiaomi", + "free": false, + "pi": 0.435, + "po": 0.87, + "ii": 29.9, + "fc": 45.4, + "scicode": 60.9, + "tb21": null, + "tb40": 34.8, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": 37.5, + "auto": 58.6, + "gpqa": null, + "critpt": 26.6, + "hle": 49.4, + "lcr": 86.3, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": 19.2, + "ctx": 1048576 + }, + { + "id": "gemini-4-argon", + "n": "Gemini 4 Argon", + "lab": "google", + "free": false, + "pi": 2, + "po": 10, + "ii": 50.4, + "fc": 43.5, + "scicode": 61.8, + "tb21": null, + "tb40": 57.1, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": 48.8, + "auto": 77.5, + "gpqa": null, + "critpt": 27.1, + "hle": 57.1, + "lcr": 79.7, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": 21.8, + "ctx": 1048576 + }, + { + "id": "minimax-m3.1-flash", + "n": "MiniMax M3.1 Flash", + "lab": "minimax", + "free": false, + "pi": 0.15, + "po": 0.6, + "ii": 29.1, + "fc": 38.6, + "scicode": 53.4, + "tb21": null, + "tb40": 25.8, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": 72.5, + "gpqa": null, + "critpt": 22.3, + "hle": 48, + "lcr": 79.7, + "ifbench": null, + "mmmu": 79.1, + "gdpv": null, + "gdppdf": 20.8, + "ctx": 1000000 + }, + { + "id": "muse-spark-1.2-contributor", + "n": "Muse Spark 1.2 Contributor", + "lab": "meta", + "free": false, + "pi": 0.1, + "po": 0.2, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1048576 + }, + { + "id": "longcat-2.0", + "n": "LongCat-2.0", + "lab": "meituan", + "free": false, + "pi": 0.3, + "po": 1.2, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1000000 + }, + { + "id": "grok-4.7", + "n": "Grok 4.7", + "lab": "xai", + "free": false, + "pi": 2, + "po": 6, + "ii": 35.5, + "fc": 33.8, + "scicode": 57.4, + "tb21": null, + "tb40": 25.8, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": 52.5, + "auto": 65.6, + "gpqa": null, + "critpt": 17.7, + "hle": 43.1, + "lcr": 76.7, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": 20, + "ctx": 500000 + }, + { + "id": "crouton-alpha-free", + "n": "Crouton Alpha Free", + "lab": "", + "free": true, + "pi": 0, + "po": 0, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1048576 + }, { "id": "hy3", "n": "Hy3", @@ -365,174 +841,6 @@ export const RAW = [ "gdppdf": null, "ctx": 256000 }, - { - "id": "deepseek-v4.1-flash", - "n": "DeepSeek V4.1 Flash", - "lab": "deepseek", - "free": false, - "pi": 0.15, - "po": 0.6, - "ii": null, - "fc": null, - "scicode": null, - "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 1000000 - }, - { - "id": "deepseek-v4-pro", - "n": "DeepSeek V4 Pro (New)", - "lab": "deepseek", - "free": false, - "pi": 0.66, - "po": 1.98, - "ii": 23.1, - "fc": 38.8, - "scicode": 51, - "tb21": 78.7, - "tb40": 14.1, - "tbh": null, - "tau2": null, - "taub": 39.6, - "apex": null, - "analyst": null, - "auto": 56.7, - "gpqa": 92.8, - "critpt": 18, - "hle": 41, - "lcr": 80.3, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": 11.4, - "ctx": 1000000 - }, - { - "id": "gemini-4-argon-contributor", - "n": "Gemini 4 Argon Contributor", - "lab": "google", - "free": false, - "pi": 4, - "po": 20, - "ii": 50.4, - "fc": 43.5, - "scicode": 61.8, - "tb21": null, - "tb40": 57.1, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": 48.8, - "auto": 77.5, - "gpqa": null, - "critpt": 27.1, - "hle": 57.1, - "lcr": 79.7, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": 21.8, - "ctx": 1048576 - }, - { - "id": "mimo-v2.6-flash", - "n": "MiMo-V2.6-Flash", - "lab": "xiaomi", - "free": false, - "pi": 0.14, - "po": 0.28, - "ii": 26.7, - "fc": 42.1, - "scicode": 51.3, - "tb21": null, - "tb40": 22.7, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": 64.1, - "gpqa": null, - "critpt": 12, - "hle": 35.1, - "lcr": 74.3, - "ifbench": null, - "mmmu": 73.1, - "gdpv": null, - "gdppdf": 9, - "ctx": 1048576 - }, - { - "id": "iceman-contributor-free", - "n": "Iceman Contributor Free", - "lab": "", - "free": true, - "pi": 0, - "po": 0, - "ii": null, - "fc": null, - "scicode": null, - "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 262144 - }, - { - "id": "gpt-5.6-luna", - "n": "GPT-5.6 Luna", - "lab": "openai", - "free": false, - "pi": 0.2, - "po": 1.2, - "ii": null, - "fc": null, - "scicode": null, - "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 1050000 - }, { "id": "kimi-k2.7-code", "n": "Kimi K2.7 Code", @@ -562,65 +870,9 @@ export const RAW = [ "ctx": 262144 }, { - "id": "mimo-v2.5", - "n": "MiMo V2.5", - "lab": "xiaomi", - "free": false, - "pi": 0.14, - "po": 0.28, - "ii": null, - "fc": null, - "scicode": null, - "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 1000000 - }, - { - "id": "space-bunny", - "n": "Space Bunny", - "lab": "", - "free": false, - "pi": 0.15, - "po": 0.6, - "ii": null, - "fc": null, - "scicode": null, - "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 1048576 - }, - { - "id": "longcat-2.5-preview-free", - "n": "LongCat 2.5 Preview Free", - "lab": "meituan", + "id": "step-5-preview-free", + "n": "Step 5 Preview Free", + "lab": "stepfun", "free": true, "pi": 0, "po": 0, @@ -646,377 +898,97 @@ export const RAW = [ "ctx": 1000000 }, { - "id": "glm-5.2", - "n": "GLM-5.2", - "lab": "zhipuai", + "id": "step-5-preview", + "n": "Step 5 Preview", + "lab": "stepfun", "free": false, - "pi": 1.4, - "po": 4.4, - "ii": null, - "fc": null, - "scicode": null, + "pi": 1, + "po": 2.7, + "ii": 28.5, + "fc": 38.4, + "scicode": 58.9, "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 1000000 - }, - { - "id": "glm-5.3-flash", - "n": "GLM-5.3-Flash", - "lab": "zhipuai", - "free": false, - "pi": 0.15, - "po": 0.5, - "ii": 27.8, - "fc": 41, - "scicode": 51.6, - "tb21": 84.3, - "tb40": 32.8, - "tbh": null, - "tau2": null, - "taub": 47.2, - "apex": null, - "analyst": 25, - "auto": 60.4, - "gpqa": 91.2, - "critpt": 15.4, - "hle": 39.9, - "lcr": 80, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": 15.4, - "ctx": 1000000 - }, - { - "id": "gpt-6-luna", - "n": "GPT-6 Luna", - "lab": "openai", - "free": false, - "pi": 0.1, - "po": 0.5, - "ii": 27.8, - "fc": 41.9, - "scicode": 54.6, - "tb21": null, - "tb40": 12.6, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": 43.8, - "auto": 53.2, - "gpqa": null, - "critpt": 19.4, - "hle": 38.5, - "lcr": 83.3, - "ifbench": null, - "mmmu": 79.7, - "gdpv": null, - "gdppdf": 22.8, - "ctx": 1050000 - }, - { - "id": "glm-5.3", - "n": "GLM-5.3", - "lab": "zhipuai", - "free": false, - "pi": 1.4, - "po": 4.4, - "ii": 31.7, - "fc": 40.1, - "scicode": 59, - "tb21": 83.9, - "tb40": 41.9, - "tbh": null, - "tau2": null, - "taub": 50.3, - "apex": null, - "analyst": 38.8, - "auto": 62.2, - "gpqa": 91.7, - "critpt": 19.1, - "hle": 42.3, - "lcr": 79.7, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": 11.2, - "ctx": 1000000 - }, - { - "id": "qwen3.8-max", - "n": "Qwen3.8 Max", - "lab": "alibaba", - "free": false, - "pi": 2, - "po": 6, - "ii": 33.6, - "fc": 43.2, - "scicode": 52.1, - "tb21": 88.8, - "tb40": 38.9, - "tbh": null, - "tau2": null, - "taub": 47.8, - "apex": 42.4, - "analyst": 45, - "auto": 56.2, - "gpqa": 92.8, - "critpt": 17.7, - "hle": 43.1, - "lcr": 80.3, - "ifbench": null, - "mmmu": 82.8, - "gdpv": null, - "gdppdf": 22.8, - "ctx": 1000000 - }, - { - "id": "mimo-v2.5-pro", - "n": "MiMo V2.5 Pro", - "lab": "xiaomi", - "free": false, - "pi": 0.435, - "po": 0.87, - "ii": null, - "fc": null, - "scicode": null, - "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 1048576 - }, - { - "id": "claude-haiku-5-5", - "n": "Claude Haiku 5.5", - "lab": "anthropic", - "free": false, - "pi": 0.1, - "po": 0.5, - "ii": 36.2, - "fc": 41.8, - "scicode": 55, - "tb21": null, - "tb40": 32.8, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": 53.8, - "auto": 35.4, - "gpqa": null, - "critpt": 18.9, - "hle": 44.4, - "lcr": 82.7, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": 20.8, - "ctx": 1000000 - }, - { - "id": "minimax-m2.7", - "n": "MiniMax-M2.7", - "lab": "minimax", - "free": false, - "pi": 0.3, - "po": 1.2, - "ii": null, - "fc": null, - "scicode": null, - "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 204800 - }, - { - "id": "longcat-2.0", - "n": "LongCat-2.0", - "lab": "meituan", - "free": false, - "pi": 0.3, - "po": 1.2, - "ii": null, - "fc": null, - "scicode": null, - "tb21": null, - "tb40": null, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": null, - "auto": null, - "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 1000000 - }, - { - "id": "minimax-m3", - "n": "MiniMax-M3", - "lab": "minimax", - "free": false, - "pi": 0.3, - "po": 1.2, - "ii": 18.7, - "fc": 23, - "scicode": 47.1, - "tb21": 65.2, - "tb40": 2, - "tbh": 42.4, - "tau2": 88.9, - "taub": 15.3, - "apex": null, - "analyst": 10, - "auto": 21.3, - "gpqa": 92.9, - "critpt": 3.7, - "hle": 39, - "lcr": 83, - "ifbench": 82.9, - "mmmu": 78.6, - "gdpv": null, - "gdppdf": 9.8, - "ctx": 1000000 - }, - { - "id": "mimo-v2.6-pro", - "n": "MiMo-V2.6-Pro", - "lab": "xiaomi", - "free": false, - "pi": 0.435, - "po": 0.87, - "ii": 29.9, - "fc": 45.4, - "scicode": 60.9, - "tb21": null, - "tb40": 34.8, - "tbh": null, - "tau2": null, - "taub": null, - "apex": null, - "analyst": 37.5, - "auto": 58.6, - "gpqa": null, - "critpt": 26.6, - "hle": 49.4, - "lcr": 86.3, - "ifbench": null, - "mmmu": null, - "gdpv": null, - "gdppdf": 19.2, - "ctx": 1048576 - }, - { - "id": "muse-spark-1.3-contributor", - "n": "Muse Spark 1.3 Contributor", - "lab": "meta", - "free": false, - "pi": 0.1, - "po": 0.2, - "ii": 36.4, - "fc": 40.6, - "scicode": 58.8, - "tb21": 84.3, "tb40": 33.3, "tbh": null, "tau2": null, - "taub": 50.5, - "apex": null, - "analyst": 37.5, - "auto": 57.9, - "gpqa": 93.5, - "critpt": 24.9, - "hle": 48.7, - "lcr": 83, + "taub": null, + "apex": 38, + "analyst": 35, + "auto": 51, + "gpqa": null, + "critpt": 20.9, + "hle": 46.5, + "lcr": 88.3, "ifbench": null, - "mmmu": null, + "mmmu": 76.4, "gdpv": null, - "gdppdf": 26.6, - "ctx": 1048576 + "gdppdf": 14.8, + "ctx": 1000000 }, { - "id": "muse-spark-1.2-contributor", - "n": "Muse Spark 1.2 Contributor", - "lab": "meta", + "id": "gpt-5.6-luna", + "n": "GPT-5.6 Luna", + "lab": "openai", "free": false, - "pi": 0.1, - "po": 0.2, - "ii": null, + "pi": 0.2, + "po": 1.2, + "ii": 23.8, "fc": null, - "scicode": null, + "scicode": 53.6, + "tb21": 80.9, + "tb40": 11.6, + "tbh": null, + "tau2": null, + "taub": 31.1, + "apex": 35.8, + "analyst": null, + "auto": 50.2, + "gpqa": 91.1, + "critpt": 20.6, + "hle": 39.5, + "lcr": 83.7, + "ifbench": null, + "mmmu": 78.6, + "gdpv": null, + "gdppdf": 24, + "ctx": 1050000 + }, + { + "id": "kimi-k3.1-pro", + "n": "Kimi K3.1 Pro", + "lab": "moonshotai", + "free": false, + "pi": 2, + "po": 10, + "ii": 46.5, + "fc": 47.1, + "scicode": 60.8, "tb21": null, - "tb40": null, + "tb40": 67.2, "tbh": null, "tau2": null, "taub": null, "apex": null, - "analyst": null, - "auto": null, + "analyst": 38.8, + "auto": 73.3, "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, + "critpt": 24.6, + "hle": 52.5, + "lcr": 86.3, "ifbench": null, - "mmmu": null, + "mmmu": 83.9, "gdpv": null, - "gdppdf": null, + "gdppdf": 31.4, "ctx": 1048576 }, { - "id": "minimax-m3.1-flash", - "n": "MiniMax M3.1 Flash", + "id": "minimax-m3.1-flash-free", + "n": "MiniMax M3.1 Flash Free", "lab": "minimax", - "free": false, - "pi": 0.15, - "po": 0.6, - "ii": 28.9, + "free": true, + "pi": 0, + "po": 0, + "ii": 29.1, "fc": 38.6, "scicode": 53.4, "tb21": null, @@ -1036,5 +1008,89 @@ export const RAW = [ "gdpv": null, "gdppdf": 20.8, "ctx": 1000000 + }, + { + "id": "deepseek-v4-pro", + "n": "DeepSeek V4 Pro", + "lab": "deepseek", + "free": false, + "pi": 0.66, + "po": 1.98, + "ii": 23.1, + "fc": 38.8, + "scicode": 51, + "tb21": 78.7, + "tb40": 14.1, + "tbh": null, + "tau2": null, + "taub": 39.6, + "apex": null, + "analyst": null, + "auto": 56.7, + "gpqa": 92.8, + "critpt": 18, + "hle": 41, + "lcr": 80.3, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": 11.4, + "ctx": 1000000 + }, + { + "id": "hy4", + "n": "Hy4", + "lab": "tencent", + "free": false, + "pi": 0.834, + "po": 2.501, + "ii": null, + "fc": null, + "scicode": null, + "tb21": null, + "tb40": null, + "tbh": null, + "tau2": null, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, + "ifbench": null, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1048576 + }, + { + "id": "minimax-m3", + "n": "MiniMax-M3", + "lab": "minimax", + "free": false, + "pi": 0.3, + "po": 1.2, + "ii": 18.9, + "fc": 23, + "scicode": 47.1, + "tb21": 65.2, + "tb40": 2, + "tbh": 42.4, + "tau2": 88.9, + "taub": 15.3, + "apex": null, + "analyst": 10, + "auto": 21.3, + "gpqa": 92.9, + "critpt": 3.7, + "hle": 39, + "lcr": 83, + "ifbench": 82.9, + "mmmu": 78.6, + "gdpv": null, + "gdppdf": 9.8, + "ctx": 1000000 } ]; diff --git a/site/assets/history.js b/site/assets/history.js index ec2fa30..5314501 100644 --- a/site/assets/history.js +++ b/site/assets/history.js @@ -1,6 +1,30 @@ // AUTO-GENERATED by scripts/sync-catalog.mjs — do not edit by hand. // Rolling week-over-week snapshot of the Intelligence Index. export const HISTORY = [ + { + "date": "2026-11-09", + "scores": { + "gpt-6-luna": 27.9, + "claude-haiku-5-5": 36.5, + "muse-spark-1.3-contributor": 36.6, + "gemini-4-argon-contributor": 50.4, + "glm-5.3": 31.7, + "mimo-v2.6-flash": 26.7, + "beam-free": 17.7, + "glm-5.3-flash": 27.8, + "qwen3.8-max": 33.7, + "mimo-v2.6-pro": 29.9, + "gemini-4-argon": 50.4, + "minimax-m3.1-flash": 29.1, + "grok-4.7": 35.5, + "step-5-preview": 28.5, + "gpt-5.6-luna": 23.8, + "kimi-k3.1-pro": 46.5, + "minimax-m3.1-flash-free": 29.1, + "deepseek-v4-pro": 23.1, + "minimax-m3": 18.9 + } + }, { "date": "2026-11-02", "scores": { diff --git a/site/assets/history.json b/site/assets/history.json index 3ffef43..1615637 100644 --- a/site/assets/history.json +++ b/site/assets/history.json @@ -1,4 +1,28 @@ [ + { + "date": "2026-11-09", + "scores": { + "gpt-6-luna": 27.9, + "claude-haiku-5-5": 36.5, + "muse-spark-1.3-contributor": 36.6, + "gemini-4-argon-contributor": 50.4, + "glm-5.3": 31.7, + "mimo-v2.6-flash": 26.7, + "beam-free": 17.7, + "glm-5.3-flash": 27.8, + "qwen3.8-max": 33.7, + "mimo-v2.6-pro": 29.9, + "gemini-4-argon": 50.4, + "minimax-m3.1-flash": 29.1, + "grok-4.7": 35.5, + "step-5-preview": 28.5, + "gpt-5.6-luna": 23.8, + "kimi-k3.1-pro": 46.5, + "minimax-m3.1-flash-free": 29.1, + "deepseek-v4-pro": 23.1, + "minimax-m3": 18.9 + } + }, { "date": "2026-11-02", "scores": { diff --git a/site/assets/snapshot.json b/site/assets/snapshot.json index c20aaee..bc2aa1d 100644 --- a/site/assets/snapshot.json +++ b/site/assets/snapshot.json @@ -1,123 +1,93 @@ { - "generated": "2026-11-02T05:24:13.718Z", + "generated": "2026-11-09T05:24:25.577Z", "models": [ - "qwen3.7-plus", - "step-5-preview-free", - "hy4-preview", - "cat-jam-free", - "gemini-4-argon", - "beam-free", - "grok-4.7", - "minimax-m3.1-flash-free", - "qwen3.8-flash", - "step-5-preview", - "kimi-k3.1-pro", - "kimi-k3", - "hy3", - "deepseek-v4.1-flash", - "deepseek-v4-pro", - "gemini-4-argon-contributor", - "mimo-v2.6-flash", - "iceman-contributor-free", - "gpt-5.6-luna", - "kimi-k2.7-code", - "mimo-v2.5", - "space-bunny", - "longcat-2.5-preview-free", - "glm-5.2", - "glm-5.3-flash", "gpt-6-luna", - "glm-5.3", - "qwen3.8-max", - "mimo-v2.5-pro", + "deepseek-v4.1-flash", + "qwen3.8-flash", "claude-haiku-5-5", - "minimax-m2.7", - "longcat-2.0", - "minimax-m3", - "mimo-v2.6-pro", "muse-spark-1.3-contributor", + "longcat-2.5-preview-free", + "gemini-4-argon-contributor", + "qwen3.7-plus", + "glm-5.3", + "mimo-v2.6-flash", + "beam-free", + "space-bunny", + "mimo-v2.5", + "cat-jam-free", + "hy4-preview", + "minimax-m2.7", + "kimi-k3", + "glm-5.3-flash", + "iceman-contributor-free", + "glm-5.2", + "mimo-v2.5-pro", + "qwen3.8-max", + "mimo-v2.6-pro", + "gemini-4-argon", + "minimax-m3.1-flash", "muse-spark-1.2-contributor", - "minimax-m3.1-flash" + "longcat-2.0", + "grok-4.7", + "crouton-alpha-free", + "hy3", + "kimi-k2.7-code", + "step-5-preview-free", + "step-5-preview", + "gpt-5.6-luna", + "kimi-k3.1-pro", + "minimax-m3.1-flash-free", + "deepseek-v4-pro", + "hy4", + "minimax-m3" ], "scores": [ { - "id": "qwen3.7-plus", - "ii": null - }, - { - "id": "step-5-preview-free", - "ii": null - }, - { - "id": "hy4-preview", - "ii": null - }, - { - "id": "cat-jam-free", - "ii": null - }, - { - "id": "gemini-4-argon", - "ii": 50.4 - }, - { - "id": "beam-free", - "ii": 17.7 - }, - { - "id": "grok-4.7", - "ii": 34.3 - }, - { - "id": "minimax-m3.1-flash-free", - "ii": 28.9 - }, - { - "id": "qwen3.8-flash", - "ii": null - }, - { - "id": "step-5-preview", - "ii": 28.5 - }, - { - "id": "kimi-k3.1-pro", - "ii": 46 - }, - { - "id": "kimi-k3", - "ii": null - }, - { - "id": "hy3", - "ii": null + "id": "gpt-6-luna", + "ii": 27.9 }, { "id": "deepseek-v4.1-flash", "ii": null }, { - "id": "deepseek-v4-pro", - "ii": 23.1 + "id": "qwen3.8-flash", + "ii": null + }, + { + "id": "claude-haiku-5-5", + "ii": 36.5 + }, + { + "id": "muse-spark-1.3-contributor", + "ii": 36.6 + }, + { + "id": "longcat-2.5-preview-free", + "ii": null }, { "id": "gemini-4-argon-contributor", "ii": 50.4 }, + { + "id": "qwen3.7-plus", + "ii": null + }, + { + "id": "glm-5.3", + "ii": 31.7 + }, { "id": "mimo-v2.6-flash", "ii": 26.7 }, { - "id": "iceman-contributor-free", - "ii": null + "id": "beam-free", + "ii": 17.7 }, { - "id": "gpt-5.6-luna", - "ii": null - }, - { - "id": "kimi-k2.7-code", + "id": "space-bunny", "ii": null }, { @@ -125,43 +95,55 @@ "ii": null }, { - "id": "space-bunny", + "id": "cat-jam-free", "ii": null }, { - "id": "longcat-2.5-preview-free", + "id": "hy4-preview", + "ii": null + }, + { + "id": "minimax-m2.7", + "ii": null + }, + { + "id": "kimi-k3", + "ii": null + }, + { + "id": "glm-5.3-flash", + "ii": 27.8 + }, + { + "id": "iceman-contributor-free", "ii": null }, { "id": "glm-5.2", "ii": null }, - { - "id": "glm-5.3-flash", - "ii": 27.8 - }, - { - "id": "gpt-6-luna", - "ii": 27.8 - }, - { - "id": "glm-5.3", - "ii": 31.7 - }, - { - "id": "qwen3.8-max", - "ii": 33.6 - }, { "id": "mimo-v2.5-pro", "ii": null }, { - "id": "claude-haiku-5-5", - "ii": 36.2 + "id": "qwen3.8-max", + "ii": 33.7 }, { - "id": "minimax-m2.7", + "id": "mimo-v2.6-pro", + "ii": 29.9 + }, + { + "id": "gemini-4-argon", + "ii": 50.4 + }, + { + "id": "minimax-m3.1-flash", + "ii": 29.1 + }, + { + "id": "muse-spark-1.2-contributor", "ii": null }, { @@ -169,148 +151,125 @@ "ii": null }, { - "id": "minimax-m3", - "ii": 18.7 + "id": "grok-4.7", + "ii": 35.5 }, { - "id": "mimo-v2.6-pro", - "ii": 29.9 - }, - { - "id": "muse-spark-1.3-contributor", - "ii": 36.4 - }, - { - "id": "muse-spark-1.2-contributor", + "id": "crouton-alpha-free", "ii": null }, { - "id": "minimax-m3.1-flash", - "ii": 28.9 - } - ], - "newModels": [], - "removedModels": [], - "deltas": [ + "id": "hy3", + "ii": null + }, { - "id": "mimo-v2.6-pro", - "from": 46.3, - "to": 29.9, - "delta": -16.4 + "id": "kimi-k2.7-code", + "ii": null + }, + { + "id": "step-5-preview-free", + "ii": null }, { "id": "step-5-preview", - "from": 43.7, - "to": 28.5, - "delta": -15.2 + "ii": 28.5 }, { - "id": "glm-5.3-flash", - "from": 41.8, - "to": 27.8, - "delta": -14 - }, - { - "id": "minimax-m3.1-flash-free", - "from": 42.7, - "to": 28.9, - "delta": -13.8 - }, - { - "id": "minimax-m3.1-flash", - "from": 42.7, - "to": 28.9, - "delta": -13.8 - }, - { - "id": "glm-5.3", - "from": 44.8, - "to": 31.7, - "delta": -13.1 - }, - { - "id": "deepseek-v4-pro", - "from": 36, - "to": 23.1, - "delta": -12.9 - }, - { - "id": "beam-free", - "from": 30.3, - "to": 17.7, - "delta": -12.6 - }, - { - "id": "grok-4.7", - "from": 46.4, - "to": 34.3, - "delta": -12.1 - }, - { - "id": "qwen3.8-max", - "from": 45.4, - "to": 33.6, - "delta": -11.8 - }, - { - "id": "muse-spark-1.3-contributor", - "from": 48.1, - "to": 36.4, - "delta": -11.7 - }, - { - "id": "mimo-v2.6-flash", - "from": 37.9, - "to": 26.7, - "delta": -11.2 - }, - { - "id": "minimax-m3", - "from": 29.2, - "to": 18.7, - "delta": -10.5 - }, - { - "id": "gpt-6-luna", - "from": 38.1, - "to": 27.8, - "delta": -10.3 + "id": "gpt-5.6-luna", + "ii": 23.8 }, { "id": "kimi-k3.1-pro", - "from": 55.1, - "to": 46, - "delta": -9.1 + "ii": 46.5 + }, + { + "id": "minimax-m3.1-flash-free", + "ii": 29.1 + }, + { + "id": "deepseek-v4-pro", + "ii": 23.1 + }, + { + "id": "hy4", + "ii": null + }, + { + "id": "minimax-m3", + "ii": 18.9 + } + ], + "newModels": [ + "crouton-alpha-free", + "hy4" + ], + "removedModels": [], + "deltas": [ + { + "id": "grok-4.7", + "from": 34.3, + "to": 35.5, + "delta": 1.2 + }, + { + "id": "kimi-k3.1-pro", + "from": 46, + "to": 46.5, + "delta": 0.5 }, { "id": "claude-haiku-5-5", - "from": 43.4, - "to": 36.2, - "delta": -7.2 + "from": 36.2, + "to": 36.5, + "delta": 0.3 }, { - "id": "gemini-4-argon", - "from": 52.6, - "to": 50.4, - "delta": -2.2 + "id": "muse-spark-1.3-contributor", + "from": 36.4, + "to": 36.6, + "delta": 0.2 }, { - "id": "gemini-4-argon-contributor", - "from": 52.6, - "to": 50.4, - "delta": -2.2 + "id": "minimax-m3.1-flash", + "from": 28.9, + "to": 29.1, + "delta": 0.2 + }, + { + "id": "minimax-m3.1-flash-free", + "from": 28.9, + "to": 29.1, + "delta": 0.2 + }, + { + "id": "minimax-m3", + "from": 18.7, + "to": 18.9, + "delta": 0.2 + }, + { + "id": "gpt-6-luna", + "from": 27.8, + "to": 27.9, + "delta": 0.1 + }, + { + "id": "qwen3.8-max", + "from": 33.6, + "to": 33.7, + "delta": 0.1 } ], - "liveCatalogSize": 28, + "liveCatalogSize": 30, "notInLiveCatalog": [ - "step-5-preview-free", - "cat-jam-free", - "minimax-m3.1-flash-free", - "gemini-4-argon-contributor", - "mimo-v2.5", - "space-bunny", "longcat-2.5-preview-free", + "gemini-4-argon-contributor", + "space-bunny", + "mimo-v2.5", + "cat-jam-free", + "minimax-m2.7", "mimo-v2.5-pro", - "minimax-m2.7" + "step-5-preview-free", + "minimax-m3.1-flash-free" ] }