diff --git a/MODELS.md b/MODELS.md index 3a4701e..f1311f3 100644 --- a/MODELS.md +++ b/MODELS.md @@ -505,21 +505,20 @@ Long-context reasoning with tool calling at a modest price — useful for repo-s ### undefined -**meituan** · released 2026-09-25 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 1M context · text, image 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: **Coding, Agentic, Image understanding, Free tier** +Targeted for: **Agentic workflows, Productivity, Complex task execution, Open weights** -Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window. +A next-generation productivity model with significantly enhanced agent and complex task execution capabilities. -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. +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** -- Free for a limited time. -- Preview release: scores and behaviour may shift. -- Text output only — no image generation. +- Preview release with no third-party evaluations published yet, so performance is unverified outside the vendor's own numbers. +- Text input only. ### undefined @@ -539,37 +538,21 @@ Same model as the paid Step 5 Preview, without the token bill — useful for lon ### undefined -**tencent** · released 2026-08-28 · $0.834 in / $2.501 out per 1M tokens · 1.02M context · text in → text out +**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: **Agentic workflows, Productivity, Complex task execution, Open weights** +Targeted for: **Coding, Agentic, Image understanding, Free tier** -A next-generation productivity model with significantly enhanced agent and complex task execution capabilities. +Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window. -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. +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** -- Preview release with no third-party evaluations published yet, so performance is unverified outside the vendor's own numbers. -- Text input only. - -### undefined - -**undisclosed** · released 2026-10-12 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 1.05M context · text in → text out - -Targeted for: **Free tier, Coding, Agentic workflows, Structured output** - -A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs. - -An anonymous free tier aimed at agents: tool calling and structured JSON output make it useful as a sub-agent or a formatter that has to hand machine-readable results to the next step. - -*Evaluated:* no public third-party evaluation published yet. - -**Caveats** - -- No vendor, no model card, no public evaluation — verify behaviour before depending on it. -- Not listed in the live Go catalogue endpoint. +- Free for a limited time. +- Preview release: scores and behaviour may shift. +- Text output only — no image generation. ### undefined @@ -588,6 +571,23 @@ An unreleased preview model with full multimodal input and tool use, priced like - No vendor or model card — no published evaluation. - Not listed in the live Go catalogue endpoint. +### undefined + +**undisclosed** · released 2026-10-12 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 1.05M context · text in → text out + +Targeted for: **Free tier, Coding, Agentic workflows, Structured output** + +A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs. + +An anonymous free tier aimed at agents: tool calling and structured JSON output make it useful as a sub-agent or a formatter that has to hand machine-readable results to the next step. + +*Evaluated:* no public third-party evaluation published yet. + +**Caveats** + +- No vendor, no model card, no public evaluation — verify behaviour before depending on it. +- Not listed in the live Go catalogue endpoint. + ## Free models outside the Go plan ### MiMo-V2.6-Flash Free (Xiaomi) diff --git a/scripts/sync-catalog.mjs b/scripts/sync-catalog.mjs index 7339840..3e24e58 100644 --- a/scripts/sync-catalog.mjs +++ b/scripts/sync-catalog.mjs @@ -272,6 +272,27 @@ export const RAW = ${JSON.stringify(scores, null, 1)}; writeFileSync(resolve(ROOT, "site/assets/snapshot.json"), JSON.stringify(snapshot, null, 2) + "\n"); +/* --- rolling history (one entry per refresh, last 52 weeks) ---------------- */ +let history = []; +try { + history = JSON.parse(await (await import("node:fs/promises")).readFile(resolve(ROOT, "site/assets/history.json"), "utf8")); +} catch { + /* first run */ +} +const week = snapshot.generated.slice(0, 10); +if (!history.length || history[0].date !== week) { + history.unshift({ + date: week, + scores: Object.fromEntries(scores.filter((s) => s.ii !== null).map((s) => [s.id, s.ii])) + }); + history = history.slice(0, 52); +} +writeFileSync(resolve(ROOT, "site/assets/history.json"), JSON.stringify(history, null, 1) + "\n"); +writeFileSync( + resolve(ROOT, "site/assets/history.js"), + `// AUTO-GENERATED by scripts/sync-catalog.mjs — do not edit by hand.\n// Rolling week-over-week snapshot of the Intelligence Index.\nexport const HISTORY = ${JSON.stringify(history, null, 1)};\n` +); + console.log("\nnew models:", newModels.length ? newModels.join(", ") : "none"); console.log("removed models:", removedModels.length ? removedModels.join(", ") : "none"); if (deltas.length) { @@ -280,4 +301,4 @@ if (deltas.length) { } else { console.log("score changes: none"); } -console.log("\nwrote site/assets/catalog.js, evals.js, snapshot.json"); +console.log("\nwrote site/assets/catalog.js, evals.js, snapshot.json, history.json"); diff --git a/site/assets/app.js b/site/assets/app.js index 9b63212..f850780 100644 --- a/site/assets/app.js +++ b/site/assets/app.js @@ -1,4 +1,5 @@ import { CATALOG, SNAPSHOT } from "./catalog.js"; +import { HISTORY } from "./history.js"; import { RAW } from "./evals.js"; import { GO_MODELS, FREE_NOTES } from "./data.js"; @@ -77,6 +78,24 @@ MODELS.forEach((m) => { }); const scored = MODELS.filter((m) => m.ii !== null); + +// week-over-week movement of the Intelligence Index (most recent two snapshots) +const DELTA = {}; +if (HISTORY.length >= 2) { + const [now, prev] = HISTORY; + for (const [id, v] of Object.entries(now.scores || {})) { + const before = prev.scores?.[id]; + if (typeof before === "number") { + const d = Math.round((v - before) * 10) / 10; + if (d !== 0) DELTA[id] = d; + } + } +} +const nameOf = (id) => MODELS.find((m) => m.id === id)?.n || id; +const movers = Object.entries(DELTA) + .sort((a, b) => Math.abs(b[1]) - Math.abs(a[1])) + .slice(0, 5) + .map(([id, d]) => ({ name: nameOf(id), delta: d })); const topOverall = scored.slice().sort((a, b) => b.ii - a.ii)[0]; const bestValue = scored.filter((m) => !m.free).slice().sort((a, b) => b.ii / b.blend - a.ii / a.blend)[0]; const snapshotDate = (SNAPSHOT.generated || "").slice(0, 10); @@ -88,7 +107,8 @@ el("cards").innerHTML = [ ["Top overall", topOverall.n, "index " + topOverall.ii.toFixed(1)], ["Best value", bestValue.n, "index " + bestValue.ii.toFixed(1) + " at $" + bestValue.blend.toFixed(2) + "/1M"], ["Free tier", MODELS.filter((m) => m.free).length, "limited-time free models"], - ["Data snapshot", snapshotDate, "refreshed weekly by CI"] + ["Data snapshot", snapshotDate, "refreshed weekly by CI"], + ["Biggest movers", movers.length ? movers[0].name : "—", movers.length ? "index " + (movers[0].delta > 0 ? "+" : "") + movers[0].delta + " this week" : "no changes vs last run"] ].map(([k, v, s]) => `
${k}
${v}
${s}
`).join(""); /* ---------- matrix --------------------------------------------------------- */ @@ -127,7 +147,9 @@ function renderMatrix() { if (c.key === "name") return; const v = c.get(m); if (c.key === "ii") { - h += `
${v === null ? 'n/a' : `${v.toFixed(1)}`}
`; + const d = DELTA[m.id]; + const dTxt = d ? `${d > 0 ? "▲" : "▼"}${Math.abs(d).toFixed(1)}` : ""; + h += `
${v === null ? 'n/a' : `${v.toFixed(1)} ${dTxt}`}
`; return; } if (c.key === "blend") { h += `${m.free ? "$0" : "$" + v.toFixed(2)}`; return; } @@ -279,4 +301,4 @@ el("foot").innerHTML = ` • Models marked "no write-up" were added to the catalogue automatically and do not yet have a hand-written description; models with no public third-party evaluation show "n/a" rather than borrowed numbers.
• No model in the Go catalogue generates images — all are text-output. "Image understanding" means the model can read images, video, PDFs or screenshots as input.

Sources: Artificial Analysis (benchmarks, Intelligence Index), models.dev (Go catalogue, pricing, context, modalities), OpenCode Data (usage and retention) and the OpenCode Go docs (allowances, privacy). Vendor announcements for model positioning.
-Data snapshot: ${snapshotDate || "n/a"} — refreshed weekly by the weekly-eval.yml workflow.`; +Data snapshot: ${snapshotDate || "n/a"} — refreshed weekly by the weekly-eval.yml workflow. The ▲/▼ marker in the Index column is the change since the previous weekly refresh.${HISTORY.length > 1 ? ` ${HISTORY.length} weekly snapshots recorded.` : ""}`; diff --git a/site/assets/catalog.js b/site/assets/catalog.js index 17278bc..f688928 100644 --- a/site/assets/catalog.js +++ b/site/assets/catalog.js @@ -2,85 +2,53 @@ // Source: models.dev/api.json (provider "opencode-go") + Artificial Analysis. export const CATALOG = [ { - "id": "mimo-v2.5-pro", - "n": "MiMo V2.5 Pro", - "lab": "xiaomi", - "released": "2026-04-22", + "id": "hy4-preview", + "n": "Hy4 preview", + "lab": "tencent", + "released": "2026-08-28", "price": { - "in": 0.435, - "out": 0.87 + "in": 0.834, + "out": 2.501 }, "free": false, - "ctx": 1048576, + "ctx": 1024000, "modalities": "text in → text out", - "description": "MiMo pro model for strong multimodal reasoning and agent execution", - "canonical": "xiaomi/mimo-v2.5-pro", + "description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.", + "canonical": "tencent/hy4-preview", "openWeights": true }, { - "id": "step-5-preview", - "n": "Step 5 Preview", + "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": "step-5-preview-free", + "n": "Step 5 Preview Free", "lab": "stepfun", "released": "2026-09-16", "price": { - "in": 1, - "out": 2.7 + "in": 0, + "out": 0 }, - "free": false, + "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": "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, 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 - }, - { - "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": "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": "deepseek-v4.1-flash", "n": "DeepSeek V4.1 Flash", @@ -97,70 +65,6 @@ export const CATALOG = [ "canonical": "deepseek/deepseek-v4.1-flash", "openWeights": true }, - { - "id": "minimax-m2.7", - "n": "MiniMax-M2.7", - "lab": "minimax", - "released": "2026-03-18", - "price": { - "in": 0.3, - "out": 1.2 - }, - "free": false, - "ctx": 204800, - "modalities": "text in → text out", - "description": "MiniMax model for chat, coding, office work, and agentic tasks", - "canonical": "minimax/MiniMax-M2.7", - "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": false - }, - { - "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": "qwen3.7-plus", - "n": "Qwen3.7 Plus", - "lab": "alibaba", - "released": "2026-06-02", - "price": { - "in": 0.4, - "out": 1.6 - }, - "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": "longcat-2.5-preview-free", "n": "LongCat 2.5 Preview Free", @@ -177,6 +81,22 @@ export const CATALOG = [ "canonical": "meituan/longcat-2.5-preview", "openWeights": false }, + { + "id": "minimax-m2.7", + "n": "MiniMax-M2.7", + "lab": "minimax", + "released": "2026-03-18", + "price": { + "in": 0.3, + "out": 1.2 + }, + "free": false, + "ctx": 204800, + "modalities": "text in → text out", + "description": "MiniMax model for chat, coding, office work, and agentic tasks", + "canonical": "minimax/MiniMax-M2.7", + "openWeights": true + }, { "id": "mimo-v2.6-pro", "n": "MiMo-V2.6-Pro", @@ -194,115 +114,51 @@ export const CATALOG = [ "openWeights": true }, { - "id": "kimi-k2.7-code", - "n": "Kimi K2.7 Code", + "id": "kimi-k3", + "n": "Kimi K3", "lab": "moonshotai", - "released": "2026-06-12", + "released": "2026-07-16", "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": "longcat-2.0", - "n": "LongCat-2.0", - "lab": "meituan", - "released": "2026-06-30", - "price": { - "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": "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": "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 - }, - { - "id": "mimo-v2.6-flash", - "n": "MiMo-V2.6-Flash", - "lab": "xiaomi", - "released": "2026-09-22", - "price": { - "in": 0.14, - "out": 0.28 + "in": 3, + "out": 15 }, "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": "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", + "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", + "canonical": "moonshotai/kimi-k3", "openWeights": true }, { - "id": "hy4-preview", - "n": "Hy4 preview", + "id": "hy3", + "n": "Hy3", "lab": "tencent", - "released": "2026-08-28", + "released": "2026-07-06", "price": { - "in": 0.834, - "out": 2.501 + "in": 0.14, + "out": 0.58 }, "free": false, - "ctx": 1024000, + "ctx": 256000, "modalities": "text in → text out", - "description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.", - "canonical": "tencent/hy4-preview", + "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", + "canonical": "tencent/hy3", + "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 }, { @@ -322,84 +178,20 @@ export const CATALOG = [ "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": "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": "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": "muse-spark-1.2-contributor", - "n": "Muse Spark 1.2 Contributor", - "lab": "meta", - "released": "2026-08-05", - "price": { - "in": 0.1, - "out": 0.2 - }, - "free": false, - "ctx": 1048576, - "modalities": "text, image, video, pdf, audio in → text out", - "description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.", - "canonical": "meta/muse-spark-1.2", - "openWeights": false - }, - { - "id": "glm-5.3-flash", - "n": "GLM-5.3-Flash", - "lab": "zhipuai", + "id": "qwen3.8-flash", + "n": "Qwen3.8 Flash", + "lab": "alibaba", "released": "2026-08-26", "price": { "in": 0.15, - "out": 0.5 + "out": 0.47 }, "free": false, "ctx": 1000000, - "modalities": "text, image, video, pdf in → text out", - "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", - "canonical": "zhipuai/glm-5.3-flash", - "openWeights": true + "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": "qwen3.8-max", @@ -418,35 +210,51 @@ export const CATALOG = [ "openWeights": false }, { - "id": "hy3", - "n": "Hy3", - "lab": "tencent", - "released": "2026-07-06", + "id": "gpt-5.6-luna", + "n": "GPT-5.6 Luna", + "lab": "openai", + "released": "2026-07-09", "price": { - "in": 0.14, - "out": 0.58 + "in": 0.2, + "out": 1.2 }, "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 + "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": "mimo-v2.5", - "n": "MiMo V2.5", - "lab": "xiaomi", - "released": "2026-04-22", + "id": "minimax-m3", + "n": "MiniMax-M3", + "lab": "minimax", + "released": "2026-06-01", "price": { - "in": 0.14, - "out": 0.28 + "in": 0.3, + "out": 1.2 }, "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", + "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 + }, + { + "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 }, { @@ -465,6 +273,86 @@ export const CATALOG = [ "canonical": "deepseek/deepseek-v4-pro", "openWeights": true }, + { + "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, 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 + }, + { + "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": "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": "qwen3.7-plus", + "n": "Qwen3.7 Plus", + "lab": "alibaba", + "released": "2026-06-02", + "price": { + "in": 0.4, + "out": 1.6 + }, + "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": "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": "glm-5.3", "n": "GLM-5.3", @@ -482,19 +370,67 @@ export const CATALOG = [ "openWeights": true }, { - "id": "gpt-5.6-luna", - "n": "GPT-5.6 Luna", - "lab": "openai", - "released": "2026-07-09", + "id": "glm-5.3-flash", + "n": "GLM-5.3-Flash", + "lab": "zhipuai", + "released": "2026-08-26", "price": { - "in": 0.2, - "out": 1.2 + "in": 0.15, + "out": 0.5 }, "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", + "ctx": 1000000, + "modalities": "text, image, video, pdf 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": "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": "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": "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 }, { @@ -514,32 +450,96 @@ export const CATALOG = [ "openWeights": false }, { - "id": "space-bunny", - "n": "Space Bunny", - "lab": "", - "released": "2026-09-23", + "id": "mimo-v2.5", + "n": "MiMo V2.5", + "lab": "xiaomi", + "released": "2026-04-22", "price": { - "in": 0.15, - "out": 0.6 + "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": "muse-spark-1.2-contributor", + "n": "Muse Spark 1.2 Contributor", + "lab": "meta", + "released": "2026-08-05", + "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 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.", + "canonical": "meta/muse-spark-1.2", "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": "longcat-2.0", + "n": "LongCat-2.0", + "lab": "meituan", + "released": "2026-06-30", + "price": { + "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": "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 } ]; export const SNAPSHOT = { - "generated": "2026-10-21T17:08:35.051Z", + "generated": "2026-10-21T17:14:47.585Z", "models": 33, "newModels": [], "removedModels": [], "deltas": [], "notInLiveCatalog": [ "step-5-preview-free", - "cat-jam-free", - "space-bunny" + "space-bunny", + "cat-jam-free" ] }; diff --git a/site/assets/evals.js b/site/assets/evals.js index 1b84271..dd77ee8 100644 --- a/site/assets/evals.js +++ b/site/assets/evals.js @@ -2,144 +2,88 @@ // Benchmark scores from Artificial Analysis (single consistent harness), scaled to 0-100. export const RAW = [ { - "id": "mimo-v2.5-pro", - "n": "MiMo V2.5 Pro", - "lab": "xiaomi", + "id": "hy4-preview", + "n": "Hy4 preview", + "lab": "tencent", "free": false, - "pi": 0.435, - "po": 0.87, - "ii": 26, + "pi": 0.834, + "po": 2.501, + "ii": null, "fc": null, - "scicode": 50.6, - "tb21": 65.2, - "tb40": 0, - "tbh": 43.2, - "tau2": 94.2, - "taub": 9.9, - "apex": 2.4, - "analyst": 20, - "auto": 13.7, - "gpqa": 86.6, - "critpt": 4, - "hle": 35.7, - "lcr": 79.7, - "ifbench": 79.9, - "mmmu": null, - "gdpv": 31, - "gdppdf": 4, - "ctx": 1048576 - }, - { - "id": "step-5-preview", - "n": "Step 5 Preview", - "lab": "stepfun", - "free": false, - "pi": 1, - "po": 2.7, - "ii": 43.7, - "fc": 38.4, - "scicode": 58.9, + "scicode": null, "tb21": null, - "tb40": 33.3, + "tb40": null, "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": 54.3, - "gdppdf": 14.8, - "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": 48.1, - "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": 59, - "gdppdf": 26.6, - "ctx": 1048576 - }, - { - "id": "qwen3.8-flash", - "n": "Qwen3.8 Flash", - "lab": "alibaba", - "free": false, - "pi": 0.15, - "po": 0.47, - "ii": 39.8, - "fc": null, - "scicode": 50.6, - "tb21": 86.1, - "tb40": 25.3, - "tbh": null, - "tau2": null, - "taub": 45.4, "apex": null, "analyst": null, - "auto": 55.9, - "gpqa": 92.3, - "critpt": 11.1, - "hle": 38, - "lcr": 79.7, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, "ifbench": null, - "mmmu": 79.8, - "gdpv": 56.4, - "gdppdf": 15.6, + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1024000 + }, + { + "id": "claude-haiku-5-5", + "n": "Claude Haiku 5.5", + "lab": "anthropic", + "free": false, + "pi": 0.1, + "po": 0.5, + "ii": 43.4, + "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": 55.9, + "gdppdf": 20.8, "ctx": 1000000 }, { - "id": "kimi-k3", - "n": "Kimi K3", - "lab": "moonshotai", - "free": false, - "pi": 3, - "po": 15, - "ii": 43.6, - "fc": 43.6, - "scicode": 59.5, - "tb21": 85, - "tb40": 12.6, + "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": 46, - "apex": 41.3, - "analyst": 38.8, - "auto": 58.3, - "gpqa": 93.5, - "critpt": 23.4, - "hle": 46.9, - "lcr": 88.7, + "taub": null, + "apex": null, + "analyst": null, + "auto": null, + "gpqa": null, + "critpt": null, + "hle": null, + "lcr": null, "ifbench": null, - "mmmu": 80.5, - "gdpv": 51.6, - "gdppdf": 22, - "ctx": 1048576 + "mmmu": null, + "gdpv": null, + "gdppdf": null, + "ctx": 1000000 }, { "id": "deepseek-v4.1-flash", @@ -169,118 +113,6 @@ export const RAW = [ "gdppdf": 12.8, "ctx": 1000000 }, - { - "id": "minimax-m2.7", - "n": "MiniMax-M2.7", - "lab": "minimax", - "free": false, - "pi": 0.3, - "po": 1.2, - "ii": 22.8, - "fc": null, - "scicode": 50.1, - "tb21": 55.4, - "tb40": 0, - "tbh": 39.4, - "tau2": 84.8, - "taub": 9.9, - "apex": 10.6, - "analyst": 11.3, - "auto": 4.4, - "gpqa": 87.4, - "critpt": 0.6, - "hle": 29.6, - "lcr": 78.3, - "ifbench": 75.7, - "mmmu": null, - "gdpv": 25.5, - "gdppdf": 6, - "ctx": 204800 - }, - { - "id": "minimax-m3.1-flash-free", - "n": "MiniMax M3.1 Flash Free", - "lab": "minimax", - "free": true, - "pi": 0, - "po": 0, - "ii": 42.7, - "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": 47.9, - "gdppdf": 20.8, - "ctx": 1000000 - }, - { - "id": "gemini-4-argon-contributor", - "n": "Gemini 4 Argon Contributor", - "lab": "google", - "free": false, - "pi": 4, - "po": 20, - "ii": 52.6, - "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": 56.2, - "gdppdf": 21.8, - "ctx": 1048576 - }, - { - "id": "qwen3.7-plus", - "n": "Qwen3.7 Plus", - "lab": "alibaba", - "free": false, - "pi": 0.4, - "po": 1.6, - "ii": 25.2, - "fc": null, - "scicode": 46.1, - "tb21": 61, - "tb40": 1, - "tbh": 47, - "tau2": 93, - "taub": 17.5, - "apex": 22.4, - "analyst": null, - "auto": 17.4, - "gpqa": 90, - "critpt": 9.1, - "hle": 35.6, - "lcr": 73, - "ifbench": 78, - "mmmu": 80.5, - "gdpv": 13.4, - "gdppdf": 12.2, - "ctx": 1000000 - }, { "id": "longcat-2.5-preview-free", "n": "LongCat 2.5 Preview Free", @@ -309,6 +141,34 @@ export const RAW = [ "gdppdf": null, "ctx": 1000000 }, + { + "id": "minimax-m2.7", + "n": "MiniMax-M2.7", + "lab": "minimax", + "free": false, + "pi": 0.3, + "po": 1.2, + "ii": 22.8, + "fc": null, + "scicode": 50.1, + "tb21": 55.4, + "tb40": 0, + "tbh": 39.4, + "tau2": 84.8, + "taub": 9.9, + "apex": 10.6, + "analyst": 11.3, + "auto": 4.4, + "gpqa": 87.4, + "critpt": 0.6, + "hle": 29.6, + "lcr": 78.3, + "ifbench": 75.7, + "mmmu": null, + "gdpv": 25.5, + "gdppdf": 6, + "ctx": 204800 + }, { "id": "mimo-v2.6-pro", "n": "MiMo-V2.6-Pro", @@ -338,59 +198,227 @@ export const RAW = [ "ctx": 1048576 }, { - "id": "kimi-k2.7-code", - "n": "Kimi K2.7 Code", + "id": "kimi-k3", + "n": "Kimi K3", "lab": "moonshotai", "free": false, - "pi": 0.95, - "po": 4, - "ii": 25.8, - "fc": null, - "scicode": 47.8, - "tb21": 67.4, - "tb40": 1, - "tbh": 44.7, - "tau2": 90.1, - "taub": 20.2, - "apex": null, - "analyst": null, - "auto": 24.5, - "gpqa": 89.6, - "critpt": 10, - "hle": 35, - "lcr": 79.3, - "ifbench": 63.1, - "mmmu": null, - "gdpv": 26.9, - "gdppdf": 11.2, - "ctx": 262144 + "pi": 3, + "po": 15, + "ii": 43.6, + "fc": 43.6, + "scicode": 59.5, + "tb21": 85, + "tb40": 12.6, + "tbh": null, + "tau2": null, + "taub": 46, + "apex": 41.3, + "analyst": 38.8, + "auto": 58.3, + "gpqa": 93.5, + "critpt": 23.4, + "hle": 46.9, + "lcr": 88.7, + "ifbench": null, + "mmmu": 80.5, + "gdpv": 51.6, + "gdppdf": 22, + "ctx": 1048576 }, { - "id": "longcat-2.0", - "n": "LongCat-2.0", - "lab": "meituan", + "id": "hy3", + "n": "Hy3", + "lab": "tencent", + "free": false, + "pi": 0.14, + "po": 0.58, + "ii": 25.3, + "fc": null, + "scicode": 48.6, + "tb21": 64.4, + "tb40": 0.5, + "tbh": null, + "tau2": null, + "taub": 22.9, + "apex": null, + "analyst": null, + "auto": 18.4, + "gpqa": 89.7, + "critpt": 4.9, + "hle": 33.5, + "lcr": 79, + "ifbench": null, + "mmmu": null, + "gdpv": 28.3, + "gdppdf": 11.2, + "ctx": 256000 + }, + { + "id": "mimo-v2.5-pro", + "n": "MiMo V2.5 Pro", + "lab": "xiaomi", + "free": false, + "pi": 0.435, + "po": 0.87, + "ii": 26, + "fc": null, + "scicode": 50.6, + "tb21": 65.2, + "tb40": 0, + "tbh": 43.2, + "tau2": 94.2, + "taub": 9.9, + "apex": 2.4, + "analyst": 20, + "auto": 13.7, + "gpqa": 86.6, + "critpt": 4, + "hle": 35.7, + "lcr": 79.7, + "ifbench": 79.9, + "mmmu": null, + "gdpv": 31, + "gdppdf": 4, + "ctx": 1048576 + }, + { + "id": "beam-free", + "n": "Beam Free", + "lab": "reflection", + "free": true, + "pi": 0, + "po": 0, + "ii": 30.3, + "fc": null, + "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": 33.9, + "gdppdf": 11.6, + "ctx": 1048576 + }, + { + "id": "qwen3.8-flash", + "n": "Qwen3.8 Flash", + "lab": "alibaba", + "free": false, + "pi": 0.15, + "po": 0.47, + "ii": 39.8, + "fc": null, + "scicode": 50.6, + "tb21": 86.1, + "tb40": 25.3, + "tbh": null, + "tau2": null, + "taub": 45.4, + "apex": null, + "analyst": null, + "auto": 55.9, + "gpqa": 92.3, + "critpt": 11.1, + "hle": 38, + "lcr": 79.7, + "ifbench": null, + "mmmu": 79.8, + "gdpv": 56.4, + "gdppdf": 15.6, + "ctx": 1000000 + }, + { + "id": "qwen3.8-max", + "n": "Qwen3.8 Max", + "lab": "alibaba", + "free": false, + "pi": 2, + "po": 6, + "ii": 45.4, + "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": 58.2, + "gdppdf": 22.8, + "ctx": 1000000 + }, + { + "id": "gpt-5.6-luna", + "n": "GPT-5.6 Luna", + "lab": "openai", + "free": false, + "pi": 0.2, + "po": 1.2, + "ii": 37.3, + "fc": 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": 48, + "gdppdf": 24, + "ctx": 1050000 + }, + { + "id": "minimax-m3", + "n": "MiniMax-M3", + "lab": "minimax", "free": false, "pi": 0.3, "po": 1.2, - "ii": 19.1, - "fc": null, - "scicode": 36.3, - "tb21": 50.2, - "tb40": 0, - "tbh": null, - "tau2": null, - "taub": 13.2, + "ii": 29.2, + "fc": 23, + "scicode": 47.1, + "tb21": 65.2, + "tb40": 2, + "tbh": 42.4, + "tau2": 88.9, + "taub": 15.3, "apex": null, - "analyst": null, - "auto": 4.5, - "gpqa": 78, - "critpt": 2.6, - "hle": 33.7, - "lcr": 65, - "ifbench": null, - "mmmu": null, - "gdpv": 18.5, - "gdppdf": 6.4, + "analyst": 10, + "auto": 21.3, + "gpqa": 92.9, + "critpt": 3.7, + "hle": 39, + "lcr": 83, + "ifbench": 82.9, + "mmmu": 78.6, + "gdpv": 37.1, + "gdppdf": 9.8, "ctx": 1000000 }, { @@ -422,198 +450,86 @@ export const RAW = [ "ctx": 1000000 }, { - "id": "minimax-m3", - "n": "MiniMax-M3", - "lab": "minimax", + "id": "deepseek-v4-pro", + "n": "DeepSeek V4 Pro (New)", + "lab": "deepseek", "free": false, - "pi": 0.3, - "po": 1.2, - "ii": 29.2, - "fc": 23, - "scicode": 47.1, - "tb21": 65.2, - "tb40": 2, - "tbh": 42.4, - "tau2": 88.9, - "taub": 15.3, + "pi": 0.66, + "po": 1.98, + "ii": 36, + "fc": 38.8, + "scicode": 51, + "tb21": 78.7, + "tb40": 14.1, + "tbh": null, + "tau2": null, + "taub": 39.6, "apex": null, - "analyst": 10, - "auto": 21.3, - "gpqa": 92.9, - "critpt": 3.7, - "hle": 39, - "lcr": 83, - "ifbench": 82.9, - "mmmu": 78.6, - "gdpv": 37.1, - "gdppdf": 9.8, + "analyst": null, + "auto": 56.7, + "gpqa": 92.8, + "critpt": 18, + "hle": 41, + "lcr": 80.3, + "ifbench": null, + "mmmu": null, + "gdpv": 47.4, + "gdppdf": 11.4, "ctx": 1000000 }, { - "id": "mimo-v2.6-flash", - "n": "MiMo-V2.6-Flash", - "lab": "xiaomi", - "free": false, - "pi": 0.14, - "po": 0.28, - "ii": 37.9, - "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": 55.4, - "gdppdf": 9, - "ctx": 1048576 - }, - { - "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": "beam-free", - "n": "Beam Free", - "lab": "reflection", - "free": true, - "pi": 0, - "po": 0, - "ii": 30.3, - "fc": null, - "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": 33.9, - "gdppdf": 11.6, - "ctx": 1048576 - }, - { - "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": "claude-haiku-5-5", - "n": "Claude Haiku 5.5", - "lab": "anthropic", + "id": "muse-spark-1.3-contributor", + "n": "Muse Spark 1.3 Contributor", + "lab": "meta", "free": false, "pi": 0.1, - "po": 0.5, - "ii": 43.4, - "fc": 41.8, - "scicode": 55, + "po": 0.2, + "ii": 48.1, + "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": 59, + "gdppdf": 26.6, + "ctx": 1048576 + }, + { + "id": "minimax-m3.1-flash-free", + "n": "MiniMax M3.1 Flash Free", + "lab": "minimax", + "free": true, + "pi": 0, + "po": 0, + "ii": 42.7, + "fc": 38.6, + "scicode": 53.4, "tb21": null, - "tb40": 32.8, + "tb40": 25.8, "tbh": null, "tau2": null, "taub": null, "apex": null, - "analyst": 53.8, - "auto": 35.4, + "analyst": null, + "auto": 72.5, "gpqa": null, - "critpt": 18.9, - "hle": 44.4, - "lcr": 82.7, + "critpt": 22.3, + "hle": 48, + "lcr": 79.7, "ifbench": null, - "mmmu": null, - "gdpv": 55.9, + "mmmu": 79.1, + "gdpv": 47.9, "gdppdf": 20.8, "ctx": 1000000 }, @@ -646,172 +562,60 @@ export const RAW = [ "ctx": 500000 }, { - "id": "muse-spark-1.2-contributor", - "n": "Muse Spark 1.2 Contributor", - "lab": "meta", - "free": false, - "pi": 0.1, - "po": 0.2, - "ii": 39.6, - "fc": null, - "scicode": 57.4, - "tb21": 80.1, - "tb40": 7.1, - "tbh": null, - "tau2": null, - "taub": 34.8, - "apex": null, - "analyst": null, - "auto": 40.6, - "gpqa": 90.4, - "critpt": 17.7, - "hle": 45.5, - "lcr": 79, - "ifbench": null, - "mmmu": null, - "gdpv": 48.6, - "gdppdf": 17.4, - "ctx": 1048576 - }, - { - "id": "glm-5.3-flash", - "n": "GLM-5.3-Flash", - "lab": "zhipuai", - "free": false, - "pi": 0.15, - "po": 0.5, - "ii": 41.8, - "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": 57.1, - "gdppdf": 15.4, - "ctx": 1000000 - }, - { - "id": "qwen3.8-max", - "n": "Qwen3.8 Max", + "id": "qwen3.7-plus", + "n": "Qwen3.7 Plus", "lab": "alibaba", "free": false, - "pi": 2, - "po": 6, - "ii": 45.4, - "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": 58.2, - "gdppdf": 22.8, - "ctx": 1000000 - }, - { - "id": "hy3", - "n": "Hy3", - "lab": "tencent", - "free": false, - "pi": 0.14, - "po": 0.58, - "ii": 25.3, + "pi": 0.4, + "po": 1.6, + "ii": 25.2, "fc": null, - "scicode": 48.6, - "tb21": 64.4, - "tb40": 0.5, - "tbh": null, - "tau2": null, - "taub": 22.9, - "apex": null, + "scicode": 46.1, + "tb21": 61, + "tb40": 1, + "tbh": 47, + "tau2": 93, + "taub": 17.5, + "apex": 22.4, "analyst": null, - "auto": 18.4, - "gpqa": 89.7, - "critpt": 4.9, - "hle": 33.5, - "lcr": 79, - "ifbench": null, - "mmmu": null, - "gdpv": 28.3, - "gdppdf": 11.2, - "ctx": 256000 - }, - { - "id": "mimo-v2.5", - "n": "MiMo V2.5", - "lab": "xiaomi", - "free": false, - "pi": 0.14, - "po": 0.28, - "ii": 21.8, - "fc": null, - "scicode": 43.9, - "tb21": 63.7, - "tb40": 0, - "tbh": 41.7, - "tau2": 90.6, - "taub": 8.7, - "apex": null, - "analyst": null, - "auto": 18.4, - "gpqa": 84.9, - "critpt": 3.7, - "hle": 27.2, + "auto": 17.4, + "gpqa": 90, + "critpt": 9.1, + "hle": 35.6, "lcr": 73, - "ifbench": 67.1, - "mmmu": 75.4, - "gdpv": 24.9, - "gdppdf": 4, + "ifbench": 78, + "mmmu": 80.5, + "gdpv": 13.4, + "gdppdf": 12.2, "ctx": 1000000 }, { - "id": "deepseek-v4-pro", - "n": "DeepSeek V4 Pro (New)", - "lab": "deepseek", + "id": "gemini-4-argon-contributor", + "n": "Gemini 4 Argon Contributor", + "lab": "google", "free": false, - "pi": 0.66, - "po": 1.98, - "ii": 36, - "fc": 38.8, - "scicode": 51, - "tb21": 78.7, - "tb40": 14.1, + "pi": 4, + "po": 20, + "ii": 52.6, + "fc": 43.5, + "scicode": 61.8, + "tb21": null, + "tb40": 57.1, "tbh": null, "tau2": null, - "taub": 39.6, + "taub": null, "apex": null, - "analyst": null, - "auto": 56.7, - "gpqa": 92.8, - "critpt": 18, - "hle": 41, - "lcr": 80.3, + "analyst": 48.8, + "auto": 77.5, + "gpqa": null, + "critpt": 27.1, + "hle": 57.1, + "lcr": 79.7, "ifbench": null, "mmmu": null, - "gdpv": 47.4, - "gdppdf": 11.4, - "ctx": 1000000 + "gdpv": 56.2, + "gdppdf": 21.8, + "ctx": 1048576 }, { "id": "glm-5.3", @@ -842,32 +646,116 @@ export const RAW = [ "ctx": 1000000 }, { - "id": "gpt-5.6-luna", - "n": "GPT-5.6 Luna", - "lab": "openai", + "id": "glm-5.3-flash", + "n": "GLM-5.3-Flash", + "lab": "zhipuai", "free": false, - "pi": 0.2, - "po": 1.2, - "ii": 37.3, - "fc": null, - "scicode": 53.6, - "tb21": 80.9, - "tb40": 11.6, + "pi": 0.15, + "po": 0.5, + "ii": 41.8, + "fc": 41, + "scicode": 51.6, + "tb21": 84.3, + "tb40": 32.8, "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, + "taub": 47.2, + "apex": null, + "analyst": 25, + "auto": 60.4, + "gpqa": 91.2, + "critpt": 15.4, + "hle": 39.9, + "lcr": 80, "ifbench": null, - "mmmu": 78.6, - "gdpv": 48, - "gdppdf": 24, - "ctx": 1050000 + "mmmu": null, + "gdpv": 57.1, + "gdppdf": 15.4, + "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": "kimi-k2.7-code", + "n": "Kimi K2.7 Code", + "lab": "moonshotai", + "free": false, + "pi": 0.95, + "po": 4, + "ii": 25.8, + "fc": null, + "scicode": 47.8, + "tb21": 67.4, + "tb40": 1, + "tbh": 44.7, + "tau2": 90.1, + "taub": 20.2, + "apex": null, + "analyst": null, + "auto": 24.5, + "gpqa": 89.6, + "critpt": 10, + "hle": 35, + "lcr": 79.3, + "ifbench": 63.1, + "mmmu": null, + "gdpv": 26.9, + "gdppdf": 11.2, + "ctx": 262144 + }, + { + "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": "gpt-6-luna", @@ -898,31 +786,143 @@ export const RAW = [ "ctx": 1050000 }, { - "id": "space-bunny", - "n": "Space Bunny", - "lab": "", + "id": "mimo-v2.5", + "n": "MiMo V2.5", + "lab": "xiaomi", "free": false, - "pi": 0.15, - "po": 0.6, - "ii": null, + "pi": 0.14, + "po": 0.28, + "ii": 21.8, "fc": null, - "scicode": null, + "scicode": 43.9, + "tb21": 63.7, + "tb40": 0, + "tbh": 41.7, + "tau2": 90.6, + "taub": 8.7, + "apex": null, + "analyst": null, + "auto": 18.4, + "gpqa": 84.9, + "critpt": 3.7, + "hle": 27.2, + "lcr": 73, + "ifbench": 67.1, + "mmmu": 75.4, + "gdpv": 24.9, + "gdppdf": 4, + "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": 39.6, + "fc": null, + "scicode": 57.4, + "tb21": 80.1, + "tb40": 7.1, + "tbh": null, + "tau2": null, + "taub": 34.8, + "apex": null, + "analyst": null, + "auto": 40.6, + "gpqa": 90.4, + "critpt": 17.7, + "hle": 45.5, + "lcr": 79, + "ifbench": null, + "mmmu": null, + "gdpv": 48.6, + "gdppdf": 17.4, + "ctx": 1048576 + }, + { + "id": "mimo-v2.6-flash", + "n": "MiMo-V2.6-Flash", + "lab": "xiaomi", + "free": false, + "pi": 0.14, + "po": 0.28, + "ii": 37.9, + "fc": 42.1, + "scicode": 51.3, "tb21": null, - "tb40": null, + "tb40": 22.7, "tbh": null, "tau2": null, "taub": null, "apex": null, "analyst": null, - "auto": null, + "auto": 64.1, "gpqa": null, - "critpt": null, - "hle": null, - "lcr": null, + "critpt": 12, + "hle": 35.1, + "lcr": 74.3, + "ifbench": null, + "mmmu": 73.1, + "gdpv": 55.4, + "gdppdf": 9, + "ctx": 1048576 + }, + { + "id": "longcat-2.0", + "n": "LongCat-2.0", + "lab": "meituan", + "free": false, + "pi": 0.3, + "po": 1.2, + "ii": 19.1, + "fc": null, + "scicode": 36.3, + "tb21": 50.2, + "tb40": 0, + "tbh": null, + "tau2": null, + "taub": 13.2, + "apex": null, + "analyst": null, + "auto": 4.5, + "gpqa": 78, + "critpt": 2.6, + "hle": 33.7, + "lcr": 65, "ifbench": null, "mmmu": null, - "gdpv": null, - "gdppdf": null, - "ctx": 1048576 + "gdpv": 18.5, + "gdppdf": 6.4, + "ctx": 1000000 + }, + { + "id": "step-5-preview", + "n": "Step 5 Preview", + "lab": "stepfun", + "free": false, + "pi": 1, + "po": 2.7, + "ii": 43.7, + "fc": 38.4, + "scicode": 58.9, + "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": 54.3, + "gdppdf": 14.8, + "ctx": 1000000 } ]; diff --git a/site/assets/history.js b/site/assets/history.js new file mode 100644 index 0000000..18567ae --- /dev/null +++ b/site/assets/history.js @@ -0,0 +1,37 @@ +// 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": "2026-10-21", + "scores": { + "claude-haiku-5-5": 43.4, + "deepseek-v4.1-flash": 39.5, + "minimax-m2.7": 22.8, + "mimo-v2.6-pro": 46.3, + "kimi-k3": 43.6, + "hy3": 25.3, + "mimo-v2.5-pro": 26, + "beam-free": 30.3, + "qwen3.8-flash": 39.8, + "qwen3.8-max": 45.4, + "gpt-5.6-luna": 37.3, + "minimax-m3": 29.2, + "glm-5.2": 33.7, + "deepseek-v4-pro": 36, + "muse-spark-1.3-contributor": 48.1, + "minimax-m3.1-flash-free": 42.7, + "grok-4.7": 46.4, + "qwen3.7-plus": 25.2, + "gemini-4-argon-contributor": 52.6, + "glm-5.3": 44.8, + "glm-5.3-flash": 41.8, + "kimi-k2.7-code": 25.8, + "gpt-6-luna": 38.1, + "mimo-v2.5": 21.8, + "muse-spark-1.2-contributor": 39.6, + "mimo-v2.6-flash": 37.9, + "longcat-2.0": 19.1, + "step-5-preview": 43.7 + } + } +]; diff --git a/site/assets/history.json b/site/assets/history.json new file mode 100644 index 0000000..b9e7445 --- /dev/null +++ b/site/assets/history.json @@ -0,0 +1,35 @@ +[ + { + "date": "2026-10-21", + "scores": { + "claude-haiku-5-5": 43.4, + "deepseek-v4.1-flash": 39.5, + "minimax-m2.7": 22.8, + "mimo-v2.6-pro": 46.3, + "kimi-k3": 43.6, + "hy3": 25.3, + "mimo-v2.5-pro": 26, + "beam-free": 30.3, + "qwen3.8-flash": 39.8, + "qwen3.8-max": 45.4, + "gpt-5.6-luna": 37.3, + "minimax-m3": 29.2, + "glm-5.2": 33.7, + "deepseek-v4-pro": 36, + "muse-spark-1.3-contributor": 48.1, + "minimax-m3.1-flash-free": 42.7, + "grok-4.7": 46.4, + "qwen3.7-plus": 25.2, + "gemini-4-argon-contributor": 52.6, + "glm-5.3": 44.8, + "glm-5.3-flash": 41.8, + "kimi-k2.7-code": 25.8, + "gpt-6-luna": 38.1, + "mimo-v2.5": 21.8, + "muse-spark-1.2-contributor": 39.6, + "mimo-v2.6-flash": 37.9, + "longcat-2.0": 19.1, + "step-5-preview": 43.7 + } + } +] diff --git a/site/assets/snapshot.json b/site/assets/snapshot.json index b4bbd32..23b1ba2 100644 --- a/site/assets/snapshot.json +++ b/site/assets/snapshot.json @@ -1,172 +1,172 @@ { - "generated": "2026-10-21T17:08:35.051Z", + "generated": "2026-10-21T17:14:47.585Z", "models": [ - "mimo-v2.5-pro", - "step-5-preview", - "muse-spark-1.3-contributor", - "qwen3.8-flash", - "kimi-k3", - "deepseek-v4.1-flash", - "minimax-m2.7", - "minimax-m3.1-flash-free", - "gemini-4-argon-contributor", - "qwen3.7-plus", - "longcat-2.5-preview-free", - "mimo-v2.6-pro", - "kimi-k2.7-code", - "longcat-2.0", - "glm-5.2", - "minimax-m3", - "mimo-v2.6-flash", - "step-5-preview-free", "hy4-preview", - "beam-free", - "cat-jam-free", "claude-haiku-5-5", - "grok-4.7", - "muse-spark-1.2-contributor", - "glm-5.3-flash", - "qwen3.8-max", + "step-5-preview-free", + "deepseek-v4.1-flash", + "longcat-2.5-preview-free", + "minimax-m2.7", + "mimo-v2.6-pro", + "kimi-k3", "hy3", - "mimo-v2.5", - "deepseek-v4-pro", - "glm-5.3", + "mimo-v2.5-pro", + "beam-free", + "qwen3.8-flash", + "qwen3.8-max", "gpt-5.6-luna", + "minimax-m3", + "glm-5.2", + "deepseek-v4-pro", + "muse-spark-1.3-contributor", + "minimax-m3.1-flash-free", + "grok-4.7", + "qwen3.7-plus", + "gemini-4-argon-contributor", + "glm-5.3", + "glm-5.3-flash", + "space-bunny", + "kimi-k2.7-code", + "cat-jam-free", "gpt-6-luna", - "space-bunny" + "mimo-v2.5", + "muse-spark-1.2-contributor", + "mimo-v2.6-flash", + "longcat-2.0", + "step-5-preview" ], "scores": [ - { - "id": "mimo-v2.5-pro", - "ii": 26 - }, - { - "id": "step-5-preview", - "ii": 43.7 - }, - { - "id": "muse-spark-1.3-contributor", - "ii": 48.1 - }, - { - "id": "qwen3.8-flash", - "ii": 39.8 - }, - { - "id": "kimi-k3", - "ii": 43.6 - }, - { - "id": "deepseek-v4.1-flash", - "ii": 39.5 - }, - { - "id": "minimax-m2.7", - "ii": 22.8 - }, - { - "id": "minimax-m3.1-flash-free", - "ii": 42.7 - }, - { - "id": "gemini-4-argon-contributor", - "ii": 52.6 - }, - { - "id": "qwen3.7-plus", - "ii": 25.2 - }, - { - "id": "longcat-2.5-preview-free", - "ii": null - }, - { - "id": "mimo-v2.6-pro", - "ii": 46.3 - }, - { - "id": "kimi-k2.7-code", - "ii": 25.8 - }, - { - "id": "longcat-2.0", - "ii": 19.1 - }, - { - "id": "glm-5.2", - "ii": 33.7 - }, - { - "id": "minimax-m3", - "ii": 29.2 - }, - { - "id": "mimo-v2.6-flash", - "ii": 37.9 - }, - { - "id": "step-5-preview-free", - "ii": null - }, { "id": "hy4-preview", "ii": null }, - { - "id": "beam-free", - "ii": 30.3 - }, - { - "id": "cat-jam-free", - "ii": null - }, { "id": "claude-haiku-5-5", "ii": 43.4 }, { - "id": "grok-4.7", - "ii": 46.4 + "id": "step-5-preview-free", + "ii": null }, { - "id": "muse-spark-1.2-contributor", - "ii": 39.6 + "id": "deepseek-v4.1-flash", + "ii": 39.5 }, { - "id": "glm-5.3-flash", - "ii": 41.8 + "id": "longcat-2.5-preview-free", + "ii": null }, { - "id": "qwen3.8-max", - "ii": 45.4 + "id": "minimax-m2.7", + "ii": 22.8 + }, + { + "id": "mimo-v2.6-pro", + "ii": 46.3 + }, + { + "id": "kimi-k3", + "ii": 43.6 }, { "id": "hy3", "ii": 25.3 }, { - "id": "mimo-v2.5", - "ii": 21.8 + "id": "mimo-v2.5-pro", + "ii": 26 }, { - "id": "deepseek-v4-pro", - "ii": 36 + "id": "beam-free", + "ii": 30.3 }, { - "id": "glm-5.3", - "ii": 44.8 + "id": "qwen3.8-flash", + "ii": 39.8 + }, + { + "id": "qwen3.8-max", + "ii": 45.4 }, { "id": "gpt-5.6-luna", "ii": 37.3 }, { - "id": "gpt-6-luna", - "ii": 38.1 + "id": "minimax-m3", + "ii": 29.2 + }, + { + "id": "glm-5.2", + "ii": 33.7 + }, + { + "id": "deepseek-v4-pro", + "ii": 36 + }, + { + "id": "muse-spark-1.3-contributor", + "ii": 48.1 + }, + { + "id": "minimax-m3.1-flash-free", + "ii": 42.7 + }, + { + "id": "grok-4.7", + "ii": 46.4 + }, + { + "id": "qwen3.7-plus", + "ii": 25.2 + }, + { + "id": "gemini-4-argon-contributor", + "ii": 52.6 + }, + { + "id": "glm-5.3", + "ii": 44.8 + }, + { + "id": "glm-5.3-flash", + "ii": 41.8 }, { "id": "space-bunny", "ii": null + }, + { + "id": "kimi-k2.7-code", + "ii": 25.8 + }, + { + "id": "cat-jam-free", + "ii": null + }, + { + "id": "gpt-6-luna", + "ii": 38.1 + }, + { + "id": "mimo-v2.5", + "ii": 21.8 + }, + { + "id": "muse-spark-1.2-contributor", + "ii": 39.6 + }, + { + "id": "mimo-v2.6-flash", + "ii": 37.9 + }, + { + "id": "longcat-2.0", + "ii": 19.1 + }, + { + "id": "step-5-preview", + "ii": 43.7 } ], "newModels": [], @@ -175,7 +175,7 @@ "liveCatalogSize": 37, "notInLiveCatalog": [ "step-5-preview-free", - "cat-jam-free", - "space-bunny" + "space-bunny", + "cat-jam-free" ] }