From f3259fdc0a73b69b21245ffd7c933f4cee2e270e Mon Sep 17 00:00:00 2001
From: opencode-go-evals <opencode-go-evals@wallacenet.ca>
Date: Mon, 26 Oct 2026 05:24:20 +0000
Subject: [PATCH] chore: weekly evaluation refresh 2026-10-26

---
 MODELS.md                 |   78 +-
 site/assets/catalog.js    |  822 +++++++++++----------
 site/assets/evals.js      | 1452 ++++++++++++++++++++-----------------
 site/assets/history.js    |   36 +
 site/assets/history.json  |   36 +
 site/assets/snapshot.json |  268 ++++---
 6 files changed, 1508 insertions(+), 1184 deletions(-)

diff --git a/MODELS.md b/MODELS.md
index f1311f3..e6d93cd 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: **2026-10-21**.
+Catalogue metadata comes from models.dev's OpenCode Go provider. Data snapshot: **2026-10-26**.
 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,
@@ -28,6 +28,16 @@ The interactive version with the full task matrix lives at `site/index.html`.
 
 ### 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 55.1 · FrontierCode 47.1 · TB4.0 67.2 · AutomationBench 73.3 · HLE 52.5 · LCR 86.3 · MMMU-Pro 83.9
+
+### 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**
@@ -46,6 +56,16 @@ 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 52.6 · FrontierCode 43.5 · TB4.0 57.1 · AutomationBench 77.5 · HLE 57.1 · LCR 79.7
+
+### undefined
+
 **meta** · released 2026-09-02 · $0.1 in / $0.2 out per 1M tokens · 1.05M context · text, image, video, pdf, audio in → text out
 
 Targeted for: **Long-horizon agents, Multi-agent workflows, Coding, Multimodal, Cheap**
@@ -183,6 +203,16 @@ Anything that has to answer fast and often: interactive completions, classificat
 
 ### 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 42.7 · 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**
@@ -200,7 +230,7 @@ Day-to-day coding-agent work on real repositories: reading long codebases, editi
 
 ### undefined
 
-**zhipuai** · released 2026-08-26 · $0.15 in / $0.5 out per 1M tokens · 1M context · text, image, video, pdf in → text out
+**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**
 
@@ -360,7 +390,7 @@ Reflection's first open-weight model: a 501B-parameter sparse Mixture-of-Experts
 
 Cost-efficient coding and agent loops. The MoE design activates only 23B parameters per token, so it is a cheap way to run a lot of terminal work, tool calls and multi-step reasoning. Text-only, so it is a pure code/reasoning worker rather than a perception model.
 
-*Evaluated:* Intelligence Index 30.3 · TB4.0 3 · AutomationBench 48.5 · HLE 34.7 · LCR 78
+*Evaluated:* Intelligence Index 30.3 · FrontierCode 24.3 · TB4.0 3 · AutomationBench 48.5 · HLE 34.7 · LCR 78
 
 **Caveats**
 
@@ -505,20 +535,20 @@ Long-context reasoning with tool calling at a modest price — useful for repo-s
 
 ### undefined
 
-**tencent** · released 2026-08-28 · $0.834 in / $2.501 out per 1M tokens · 1.02M context · text in → text out
+**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: **Agentic workflows, Productivity, Complex task execution, Open weights**
+Targeted for: **Free tier, Coding, Agentic workflows, Structured output**
 
-A next-generation productivity model with significantly enhanced agent and complex task execution capabilities.
+A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.
 
-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.
+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**
 
-- Preview release with no third-party evaluations published yet, so performance is unverified outside the vendor's own numbers.
-- Text input only.
+- No vendor, no model card, no public evaluation — verify behaviour before depending on it.
+- Not listed in the live Go catalogue endpoint.
 
 ### undefined
 
@@ -538,6 +568,23 @@ 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
+
+Targeted for: **Agentic workflows, Productivity, Complex task execution, Open weights**
+
+A next-generation productivity model with significantly enhanced agent and complex task execution capabilities.
+
+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**
+
+- Preview release with no third-party evaluations published yet, so performance is unverified outside the vendor's own numbers.
+- Text input only.
+
+### 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**
@@ -573,21 +620,14 @@ An unreleased preview model with full multimodal input and tool use, priced like
 
 ### undefined
 
-**undisclosed** · released 2026-10-12 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 1.05M context · text in → text out
+**undisclosed** · released 2026-10-24 · $0 in / $0 out per 1M tokens · **free tier (limited time)** · 0.26M context · text in → text out
 
-Targeted for: **Free tier, Coding, Agentic workflows, Structured output**
+Stealth model, free for a limited time
 
-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.
+_No hand-written write-up yet._
 
 *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/site/assets/catalog.js b/site/assets/catalog.js
index f688928..b55c490 100644
--- a/site/assets/catalog.js
+++ b/site/assets/catalog.js
@@ -2,227 +2,35 @@
 // Source: models.dev/api.json (provider "opencode-go") + Artificial Analysis.
 export const CATALOG = [
  {
-  "id": "hy4-preview",
-  "n": "Hy4 preview",
-  "lab": "tencent",
-  "released": "2026-08-28",
+  "id": "mimo-v2.5",
+  "n": "MiMo V2.5",
+  "lab": "xiaomi",
+  "released": "2026-04-22",
   "price": {
-   "in": 0.834,
-   "out": 2.501
+   "in": 0.14,
+   "out": 0.28
   },
   "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",
+  "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": "claude-haiku-5-5",
-  "n": "Claude Haiku 5.5",
-  "lab": "anthropic",
-  "released": "2026-10-07",
+  "id": "gpt-6-luna",
+  "n": "GPT-6 Luna",
+  "lab": "openai",
+  "released": "2026-09-22",
   "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": 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": "deepseek-v4.1-flash",
-  "n": "DeepSeek V4.1 Flash",
-  "lab": "deepseek",
-  "released": "2026-09-10",
-  "price": {
-   "in": 0.15,
-   "out": 0.6
-  },
-  "free": false,
-  "ctx": 1000000,
-  "modalities": "text, image in → text out",
-  "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
-  "canonical": "deepseek/deepseek-v4.1-flash",
-  "openWeights": true
- },
- {
-  "id": "longcat-2.5-preview-free",
-  "n": "LongCat 2.5 Preview Free",
-  "lab": "meituan",
-  "released": "2026-09-25",
-  "price": {
-   "in": 0,
-   "out": 0
-  },
-  "free": true,
-  "ctx": 1000000,
-  "modalities": "text, image in → text out",
-  "description": "Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window",
-  "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",
-  "lab": "xiaomi",
-  "released": "2026-09-22",
-  "price": {
-   "in": 0.435,
-   "out": 0.87
-  },
-  "free": false,
-  "ctx": 1048576,
-  "modalities": "text, image, audio, video in → text out",
-  "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
-  "canonical": "xiaomi/mimo-v2.6-pro",
-  "openWeights": true
- },
- {
-  "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": "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": "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": "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": "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": "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",
+  "description": "OpenAI's most efficient model for focused, high-volume tasks",
+  "canonical": "openai/gpt-6-luna",
   "openWeights": false
  },
  {
@@ -242,35 +50,51 @@ export const CATALOG = [
   "openWeights": true
  },
  {
-  "id": "glm-5.2",
-  "n": "GLM-5.2",
-  "lab": "zhipuai",
-  "released": "2026-06-13",
+  "id": "hy3",
+  "n": "Hy3",
+  "lab": "tencent",
+  "released": "2026-07-06",
   "price": {
-   "in": 1.4,
-   "out": 4.4
+   "in": 0.14,
+   "out": 0.58
   },
   "free": false,
-  "ctx": 1000000,
+  "ctx": 256000,
   "modalities": "text in → text out",
-  "description": "Open flagship GLM for long-horizon coding agents and million-token context work",
-  "canonical": "zhipuai/glm-5.2",
+  "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
+  "canonical": "tencent/hy3",
   "openWeights": true
  },
  {
-  "id": "deepseek-v4-pro",
-  "n": "DeepSeek V4 Pro (New)",
-  "lab": "deepseek",
-  "released": "2026-04-24",
+  "id": "cat-jam-free",
+  "n": "Cat Jam Free",
+  "lab": "",
+  "released": "2026-10-12",
   "price": {
-   "in": 0.66,
-   "out": 1.98
+   "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": "mimo-v2.6-pro",
+  "n": "MiMo-V2.6-Pro",
+  "lab": "xiaomi",
+  "released": "2026-09-22",
+  "price": {
+   "in": 0.435,
+   "out": 0.87
   },
   "free": false,
-  "ctx": 1000000,
-  "modalities": "text in → text out",
-  "description": "Flagship DeepSeek model for coding, reasoning, and agentic work",
-  "canonical": "deepseek/deepseek-v4-pro",
+  "ctx": 1048576,
+  "modalities": "text, image, audio, video in → text out",
+  "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
+  "canonical": "xiaomi/mimo-v2.6-pro",
   "openWeights": true
  },
  {
@@ -289,54 +113,6 @@ export const CATALOG = [
   "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",
@@ -353,6 +129,150 @@ export const CATALOG = [
   "canonical": "google/gemini-4-argon",
   "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": "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": 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": "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": "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": "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": "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": "glm-5.3",
   "n": "GLM-5.3",
@@ -380,107 +300,43 @@ export const CATALOG = [
   },
   "free": false,
   "ctx": 1000000,
-  "modalities": "text, image, video, pdf in → text out",
+  "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": "space-bunny",
-  "n": "Space Bunny",
-  "lab": "",
-  "released": "2026-09-23",
+  "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": "deepseek-v4.1-flash",
+  "n": "DeepSeek V4.1 Flash",
+  "lab": "deepseek",
+  "released": "2026-09-10",
   "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
- },
- {
-  "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",
-  "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, audio, video in → text out",
-  "description": "MiMo omni model for text, image, video, audio, and agents",
-  "canonical": "xiaomi/mimo-v2.5",
+  "modalities": "text, image in → text out",
+  "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
+  "canonical": "deepseek/deepseek-v4.1-flash",
   "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, 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",
@@ -497,6 +353,22 @@ export const CATALOG = [
   "canonical": "xiaomi/mimo-v2.6-flash",
   "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": "longcat-2.0",
   "n": "LongCat-2.0",
@@ -514,32 +386,232 @@ export const CATALOG = [
   "openWeights": true
  },
  {
-  "id": "step-5-preview",
-  "n": "Step 5 Preview",
-  "lab": "stepfun",
-  "released": "2026-09-16",
+  "id": "minimax-m3.1-flash",
+  "n": "MiniMax M3.1 Flash",
+  "lab": "minimax",
+  "released": "2026-10-19",
   "price": {
-   "in": 1,
-   "out": 2.7
+   "in": 0.15,
+   "out": 0.6
   },
   "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",
+  "description": "Frontier multimodal coding model with 1M context window and tunable thinking depth",
+  "canonical": "minimax/MiniMax-M3.1-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": "longcat-2.5-preview-free",
+  "n": "LongCat 2.5 Preview Free",
+  "lab": "meituan",
+  "released": "2026-09-25",
+  "price": {
+   "in": 0,
+   "out": 0
+  },
+  "free": true,
+  "ctx": 1000000,
+  "modalities": "text, image in → text out",
+  "description": "Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window",
+  "canonical": "meituan/longcat-2.5-preview",
+  "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": "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": "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-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": "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": "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": "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": "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": "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": "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
  }
 ];
 
 export const SNAPSHOT = {
- "generated": "2026-10-21T17:14:47.585Z",
- "models": 33,
- "newModels": [],
+ "generated": "2026-10-26T05:24:19.608Z",
+ "models": 37,
+ "newModels": [
+  "kimi-k3.1-pro",
+  "gemini-4-argon",
+  "minimax-m3.1-flash",
+  "iceman-contributor-free"
+ ],
  "removedModels": [],
  "deltas": [],
  "notInLiveCatalog": [
+  "cat-jam-free",
+  "gemini-4-argon-contributor",
   "step-5-preview-free",
+  "longcat-2.5-preview-free",
   "space-bunny",
-  "cat-jam-free"
+  "minimax-m3.1-flash-free"
  ]
 };
diff --git a/site/assets/evals.js b/site/assets/evals.js
index dd77ee8..371d63b 100644
--- a/site/assets/evals.js
+++ b/site/assets/evals.js
@@ -2,12 +2,124 @@
 // Benchmark scores from Artificial Analysis (single consistent harness), scaled to 0-100.
 export const RAW = [
  {
-  "id": "hy4-preview",
-  "n": "Hy4 preview",
+  "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,
+  "lcr": 73,
+  "ifbench": 67.1,
+  "mmmu": 75.4,
+  "gdpv": null,
+  "gdppdf": 4,
+  "ctx": 1000000
+ },
+ {
+  "id": "gpt-6-luna",
+  "n": "GPT-6 Luna",
+  "lab": "openai",
+  "free": false,
+  "pi": 0.1,
+  "po": 0.5,
+  "ii": 38.1,
+  "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": "minimax-m3",
+  "n": "MiniMax-M3",
+  "lab": "minimax",
+  "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,
+  "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": "hy3",
+  "n": "Hy3",
   "lab": "tencent",
   "free": false,
-  "pi": 0.834,
-  "po": 2.501,
+  "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": null,
+  "gdppdf": 11.2,
+  "ctx": 256000
+ },
+ {
+  "id": "cat-jam-free",
+  "n": "Cat Jam Free",
+  "lab": "",
+  "free": true,
+  "pi": 0,
+  "po": 0,
   "ii": null,
   "fc": null,
   "scicode": null,
@@ -27,35 +139,91 @@ export const RAW = [
   "mmmu": null,
   "gdpv": null,
   "gdppdf": null,
-  "ctx": 1024000
+  "ctx": 1048576
  },
  {
-  "id": "claude-haiku-5-5",
-  "n": "Claude Haiku 5.5",
-  "lab": "anthropic",
+  "id": "mimo-v2.6-pro",
+  "n": "MiMo-V2.6-Pro",
+  "lab": "xiaomi",
   "free": false,
-  "pi": 0.1,
-  "po": 0.5,
-  "ii": 43.4,
-  "fc": 41.8,
-  "scicode": 55,
+  "pi": 0.435,
+  "po": 0.87,
+  "ii": 46.3,
+  "fc": 45.4,
+  "scicode": 60.9,
   "tb21": null,
-  "tb40": 32.8,
+  "tb40": 34.8,
   "tbh": null,
   "tau2": null,
   "taub": null,
   "apex": null,
-  "analyst": 53.8,
-  "auto": 35.4,
+  "analyst": 37.5,
+  "auto": 58.6,
   "gpqa": null,
-  "critpt": 18.9,
-  "hle": 44.4,
-  "lcr": 82.7,
+  "critpt": 26.6,
+  "hle": 49.4,
+  "lcr": 86.3,
   "ifbench": null,
   "mmmu": null,
-  "gdpv": 55.9,
-  "gdppdf": 20.8,
-  "ctx": 1000000
+  "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": 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": null,
+  "gdppdf": 26.6,
+  "ctx": 1048576
+ },
+ {
+  "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": null,
+  "gdppdf": 21.8,
+  "ctx": 1048576
  },
  {
   "id": "step-5-preview-free",
@@ -85,6 +253,314 @@ export const RAW = [
   "gdppdf": null,
   "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": null,
+  "gdppdf": 24,
+  "ctx": 1050000
+ },
+ {
+  "id": "kimi-k3.1-pro",
+  "n": "Kimi K3.1 Pro",
+  "lab": "moonshotai",
+  "free": false,
+  "pi": 2,
+  "po": 10,
+  "ii": 55.1,
+  "fc": 47.1,
+  "scicode": 60.8,
+  "tb21": null,
+  "tb40": 67.2,
+  "tbh": null,
+  "tau2": null,
+  "taub": null,
+  "apex": null,
+  "analyst": 38.8,
+  "auto": 73.3,
+  "gpqa": null,
+  "critpt": 24.6,
+  "hle": 52.5,
+  "lcr": 86.3,
+  "ifbench": null,
+  "mmmu": 83.9,
+  "gdpv": null,
+  "gdppdf": 31.4,
+  "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": null,
+  "gdppdf": 15.6,
+  "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": null,
+  "gdppdf": 14.8,
+  "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": null,
+  "gdppdf": 22.8,
+  "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": "gemini-4-argon",
+  "n": "Gemini 4 Argon",
+  "lab": "google",
+  "free": false,
+  "pi": 2,
+  "po": 10,
+  "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": null,
+  "gdppdf": 21.8,
+  "ctx": 1048576
+ },
+ {
+  "id": "glm-5.2",
+  "n": "GLM-5.2",
+  "lab": "zhipuai",
+  "free": false,
+  "pi": 1.4,
+  "po": 4.4,
+  "ii": 33.7,
+  "fc": null,
+  "scicode": 51.2,
+  "tb21": 77.9,
+  "tb40": 1,
+  "tbh": 50.8,
+  "tau2": 99.1,
+  "taub": 34.6,
+  "apex": 33.7,
+  "analyst": null,
+  "auto": 28.4,
+  "gpqa": 89.5,
+  "critpt": 20.9,
+  "hle": 41.1,
+  "lcr": 78.3,
+  "ifbench": 73.3,
+  "mmmu": null,
+  "gdpv": null,
+  "gdppdf": 10.4,
+  "ctx": 1000000
+ },
+ {
+  "id": "glm-5.3",
+  "n": "GLM-5.3",
+  "lab": "zhipuai",
+  "free": false,
+  "pi": 1.4,
+  "po": 4.4,
+  "ii": 44.8,
+  "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": "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": null,
+  "gdppdf": 15.4,
+  "ctx": 1000000
+ },
+ {
+  "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": null,
+  "gdppdf": 12.2,
+  "ctx": 1000000
+ },
  {
   "id": "deepseek-v4.1-flash",
   "n": "DeepSeek V4.1 Flash",
@@ -109,10 +585,150 @@ export const RAW = [
   "lcr": 84,
   "ifbench": null,
   "mmmu": 77,
-  "gdpv": 55,
+  "gdpv": null,
   "gdppdf": 12.8,
   "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": null,
+  "gdppdf": 9,
+  "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": null,
+  "gdppdf": 11.2,
+  "ctx": 262144
+ },
+ {
+  "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": 6.4,
+  "ctx": 1000000
+ },
+ {
+  "id": "minimax-m3.1-flash",
+  "n": "MiniMax M3.1 Flash",
+  "lab": "minimax",
+  "free": false,
+  "pi": 0.15,
+  "po": 0.6,
+  "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": null,
+  "gdppdf": 20.8,
+  "ctx": 1000000
+ },
+ {
+  "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": null,
+  "gdppdf": 20.8,
+  "ctx": 1000000
+ },
  {
   "id": "longcat-2.5-preview-free",
   "n": "LongCat 2.5 Preview Free",
@@ -142,116 +758,32 @@ export const RAW = [
   "ctx": 1000000
  },
  {
-  "id": "minimax-m2.7",
-  "n": "MiniMax-M2.7",
-  "lab": "minimax",
+  "id": "grok-4.7",
+  "n": "Grok 4.7",
+  "lab": "xai",
   "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",
-  "lab": "xiaomi",
-  "free": false,
-  "pi": 0.435,
-  "po": 0.87,
-  "ii": 46.3,
-  "fc": 45.4,
-  "scicode": 60.9,
+  "pi": 2,
+  "po": 6,
+  "ii": 46.4,
+  "fc": 33.8,
+  "scicode": 57.4,
   "tb21": null,
-  "tb40": 34.8,
+  "tb40": 25.8,
   "tbh": null,
   "tau2": null,
   "taub": null,
   "apex": null,
-  "analyst": 37.5,
-  "auto": 58.6,
+  "analyst": 52.5,
+  "auto": 65.6,
   "gpqa": null,
-  "critpt": 26.6,
-  "hle": 49.4,
-  "lcr": 86.3,
+  "critpt": 17.7,
+  "hle": 43.1,
+  "lcr": 76.7,
   "ifbench": null,
   "mmmu": null,
-  "gdpv": 59.2,
-  "gdppdf": 19.2,
-  "ctx": 1048576
- },
- {
-  "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,
-  "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": "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
+  "gdpv": null,
+  "gdppdf": 20,
+  "ctx": 500000
  },
  {
   "id": "mimo-v2.5-pro",
@@ -277,402 +809,10 @@ export const RAW = [
   "lcr": 79.7,
   "ifbench": 79.9,
   "mmmu": null,
-  "gdpv": 31,
+  "gdpv": null,
   "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": 29.2,
-  "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": 37.1,
-  "gdppdf": 9.8,
-  "ctx": 1000000
- },
- {
-  "id": "glm-5.2",
-  "n": "GLM-5.2",
-  "lab": "zhipuai",
-  "free": false,
-  "pi": 1.4,
-  "po": 4.4,
-  "ii": 33.7,
-  "fc": null,
-  "scicode": 51.2,
-  "tb21": 77.9,
-  "tb40": 1,
-  "tbh": 50.8,
-  "tau2": 99.1,
-  "taub": 34.6,
-  "apex": 33.7,
-  "analyst": null,
-  "auto": 28.4,
-  "gpqa": 89.5,
-  "critpt": 20.9,
-  "hle": 41.1,
-  "lcr": 78.3,
-  "ifbench": 73.3,
-  "mmmu": null,
-  "gdpv": 43.6,
-  "gdppdf": 10.4,
-  "ctx": 1000000
- },
- {
-  "id": "deepseek-v4-pro",
-  "n": "DeepSeek V4 Pro (New)",
-  "lab": "deepseek",
-  "free": false,
-  "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": 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": "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": "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": "grok-4.7",
-  "n": "Grok 4.7",
-  "lab": "xai",
-  "free": false,
-  "pi": 2,
-  "po": 6,
-  "ii": 46.4,
-  "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": 60.6,
-  "gdppdf": 20,
-  "ctx": 500000
- },
- {
-  "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": "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": "glm-5.3",
-  "n": "GLM-5.3",
-  "lab": "zhipuai",
-  "free": false,
-  "pi": 1.4,
-  "po": 4.4,
-  "ii": 44.8,
-  "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": 57.5,
-  "gdppdf": 11.2,
-  "ctx": 1000000
- },
- {
-  "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": "space-bunny",
   "n": "Space Bunny",
@@ -702,36 +842,92 @@ 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": null,
+  "gdppdf": 22,
+  "ctx": 1048576
  },
  {
-  "id": "cat-jam-free",
-  "n": "Cat Jam Free",
+  "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": 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": 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": null,
+  "gdppdf": 6,
+  "ctx": 204800
+ },
+ {
+  "id": "iceman-contributor-free",
+  "n": "Iceman Contributor Free",
   "lab": "",
   "free": true,
   "pi": 0,
@@ -755,62 +951,62 @@ export const RAW = [
   "mmmu": null,
   "gdpv": null,
   "gdppdf": null,
-  "ctx": 1048576
+  "ctx": 262144
  },
  {
-  "id": "gpt-6-luna",
-  "n": "GPT-6 Luna",
-  "lab": "openai",
-  "free": false,
-  "pi": 0.1,
-  "po": 0.5,
-  "ii": 38.1,
-  "fc": 41.9,
-  "scicode": 54.6,
+  "id": "beam-free",
+  "n": "Beam Free",
+  "lab": "reflection",
+  "free": true,
+  "pi": 0,
+  "po": 0,
+  "ii": 30.3,
+  "fc": 24.3,
+  "scicode": 48.5,
   "tb21": null,
-  "tb40": 12.6,
+  "tb40": 3,
   "tbh": null,
   "tau2": null,
   "taub": null,
   "apex": null,
-  "analyst": 43.8,
-  "auto": 53.2,
+  "analyst": null,
+  "auto": 48.5,
   "gpqa": null,
-  "critpt": 19.4,
-  "hle": 38.5,
-  "lcr": 83.3,
+  "critpt": 13.1,
+  "hle": 34.7,
+  "lcr": 78,
   "ifbench": null,
-  "mmmu": 79.7,
-  "gdpv": 46.6,
-  "gdppdf": 22.8,
-  "ctx": 1050000
+  "mmmu": null,
+  "gdpv": null,
+  "gdppdf": 11.6,
+  "ctx": 1048576
  },
  {
-  "id": "mimo-v2.5",
-  "n": "MiMo V2.5",
-  "lab": "xiaomi",
+  "id": "deepseek-v4-pro",
+  "n": "DeepSeek V4 Pro (New)",
+  "lab": "deepseek",
   "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,
+  "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": 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,
+  "auto": 56.7,
+  "gpqa": 92.8,
+  "critpt": 18,
+  "hle": 41,
+  "lcr": 80.3,
+  "ifbench": null,
+  "mmmu": null,
+  "gdpv": null,
+  "gdppdf": 11.4,
   "ctx": 1000000
  },
  {
@@ -837,92 +1033,8 @@ export const RAW = [
   "lcr": 79,
   "ifbench": null,
   "mmmu": null,
-  "gdpv": 48.6,
+  "gdpv": null,
   "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": 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": "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": 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
index 18567ae..45c012e 100644
--- a/site/assets/history.js
+++ b/site/assets/history.js
@@ -1,6 +1,42 @@
 // 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": "2026-10-26",
+  "scores": {
+   "mimo-v2.5": 21.8,
+   "gpt-6-luna": 38.1,
+   "minimax-m3": 29.2,
+   "hy3": 25.3,
+   "mimo-v2.6-pro": 46.3,
+   "muse-spark-1.3-contributor": 48.1,
+   "gemini-4-argon-contributor": 52.6,
+   "gpt-5.6-luna": 37.3,
+   "kimi-k3.1-pro": 55.1,
+   "qwen3.8-flash": 39.8,
+   "step-5-preview": 43.7,
+   "qwen3.8-max": 45.4,
+   "gemini-4-argon": 52.6,
+   "glm-5.2": 33.7,
+   "glm-5.3": 44.8,
+   "glm-5.3-flash": 41.8,
+   "qwen3.7-plus": 25.2,
+   "deepseek-v4.1-flash": 39.5,
+   "mimo-v2.6-flash": 37.9,
+   "kimi-k2.7-code": 25.8,
+   "longcat-2.0": 19.1,
+   "minimax-m3.1-flash": 42.7,
+   "claude-haiku-5-5": 43.4,
+   "grok-4.7": 46.4,
+   "mimo-v2.5-pro": 26,
+   "kimi-k3": 43.6,
+   "minimax-m3.1-flash-free": 42.7,
+   "minimax-m2.7": 22.8,
+   "beam-free": 30.3,
+   "deepseek-v4-pro": 36,
+   "muse-spark-1.2-contributor": 39.6
+  }
+ },
  {
   "date": "2026-10-21",
   "scores": {
diff --git a/site/assets/history.json b/site/assets/history.json
index b9e7445..4023872 100644
--- a/site/assets/history.json
+++ b/site/assets/history.json
@@ -1,4 +1,40 @@
 [
+ {
+  "date": "2026-10-26",
+  "scores": {
+   "mimo-v2.5": 21.8,
+   "gpt-6-luna": 38.1,
+   "minimax-m3": 29.2,
+   "hy3": 25.3,
+   "mimo-v2.6-pro": 46.3,
+   "muse-spark-1.3-contributor": 48.1,
+   "gemini-4-argon-contributor": 52.6,
+   "gpt-5.6-luna": 37.3,
+   "kimi-k3.1-pro": 55.1,
+   "qwen3.8-flash": 39.8,
+   "step-5-preview": 43.7,
+   "qwen3.8-max": 45.4,
+   "gemini-4-argon": 52.6,
+   "glm-5.2": 33.7,
+   "glm-5.3": 44.8,
+   "glm-5.3-flash": 41.8,
+   "qwen3.7-plus": 25.2,
+   "deepseek-v4.1-flash": 39.5,
+   "mimo-v2.6-flash": 37.9,
+   "kimi-k2.7-code": 25.8,
+   "longcat-2.0": 19.1,
+   "minimax-m3.1-flash": 42.7,
+   "claude-haiku-5-5": 43.4,
+   "grok-4.7": 46.4,
+   "mimo-v2.5-pro": 26,
+   "kimi-k3": 43.6,
+   "minimax-m3.1-flash-free": 42.7,
+   "minimax-m2.7": 22.8,
+   "beam-free": 30.3,
+   "deepseek-v4-pro": 36,
+   "muse-spark-1.2-contributor": 39.6
+  }
+ },
  {
   "date": "2026-10-21",
   "scores": {
diff --git a/site/assets/snapshot.json b/site/assets/snapshot.json
index 23b1ba2..1bc797c 100644
--- a/site/assets/snapshot.json
+++ b/site/assets/snapshot.json
@@ -1,129 +1,113 @@
 {
-  "generated": "2026-10-21T17:14:47.585Z",
+  "generated": "2026-10-26T05:24:19.608Z",
   "models": [
-    "hy4-preview",
-    "claude-haiku-5-5",
-    "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-pro",
-    "beam-free",
-    "qwen3.8-flash",
-    "qwen3.8-max",
-    "gpt-5.6-luna",
+    "mimo-v2.5",
+    "gpt-6-luna",
     "minimax-m3",
-    "glm-5.2",
-    "deepseek-v4-pro",
+    "hy3",
+    "cat-jam-free",
+    "mimo-v2.6-pro",
     "muse-spark-1.3-contributor",
-    "minimax-m3.1-flash-free",
-    "grok-4.7",
-    "qwen3.7-plus",
     "gemini-4-argon-contributor",
+    "step-5-preview-free",
+    "gpt-5.6-luna",
+    "kimi-k3.1-pro",
+    "qwen3.8-flash",
+    "step-5-preview",
+    "qwen3.8-max",
+    "hy4-preview",
+    "gemini-4-argon",
+    "glm-5.2",
     "glm-5.3",
     "glm-5.3-flash",
-    "space-bunny",
-    "kimi-k2.7-code",
-    "cat-jam-free",
-    "gpt-6-luna",
-    "mimo-v2.5",
-    "muse-spark-1.2-contributor",
+    "qwen3.7-plus",
+    "deepseek-v4.1-flash",
     "mimo-v2.6-flash",
+    "kimi-k2.7-code",
     "longcat-2.0",
-    "step-5-preview"
+    "minimax-m3.1-flash",
+    "claude-haiku-5-5",
+    "longcat-2.5-preview-free",
+    "grok-4.7",
+    "mimo-v2.5-pro",
+    "space-bunny",
+    "kimi-k3",
+    "minimax-m3.1-flash-free",
+    "minimax-m2.7",
+    "iceman-contributor-free",
+    "beam-free",
+    "deepseek-v4-pro",
+    "muse-spark-1.2-contributor"
   ],
   "scores": [
     {
-      "id": "hy4-preview",
-      "ii": null
+      "id": "mimo-v2.5",
+      "ii": 21.8
     },
     {
-      "id": "claude-haiku-5-5",
-      "ii": 43.4
-    },
-    {
-      "id": "step-5-preview-free",
-      "ii": null
-    },
-    {
-      "id": "deepseek-v4.1-flash",
-      "ii": 39.5
-    },
-    {
-      "id": "longcat-2.5-preview-free",
-      "ii": null
-    },
-    {
-      "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-pro",
-      "ii": 26
-    },
-    {
-      "id": "beam-free",
-      "ii": 30.3
-    },
-    {
-      "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": "hy3",
+      "ii": 25.3
     },
     {
-      "id": "deepseek-v4-pro",
-      "ii": 36
+      "id": "cat-jam-free",
+      "ii": null
+    },
+    {
+      "id": "mimo-v2.6-pro",
+      "ii": 46.3
     },
     {
       "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": "step-5-preview-free",
+      "ii": null
+    },
+    {
+      "id": "gpt-5.6-luna",
+      "ii": 37.3
+    },
+    {
+      "id": "kimi-k3.1-pro",
+      "ii": 55.1
+    },
+    {
+      "id": "qwen3.8-flash",
+      "ii": 39.8
+    },
+    {
+      "id": "step-5-preview",
+      "ii": 43.7
+    },
+    {
+      "id": "qwen3.8-max",
+      "ii": 45.4
+    },
+    {
+      "id": "hy4-preview",
+      "ii": null
+    },
+    {
+      "id": "gemini-4-argon",
+      "ii": 52.6
+    },
+    {
+      "id": "glm-5.2",
+      "ii": 33.7
+    },
     {
       "id": "glm-5.3",
       "ii": 44.8
@@ -133,49 +117,93 @@
       "ii": 41.8
     },
     {
-      "id": "space-bunny",
-      "ii": null
+      "id": "qwen3.7-plus",
+      "ii": 25.2
     },
     {
-      "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": "deepseek-v4.1-flash",
+      "ii": 39.5
     },
     {
       "id": "mimo-v2.6-flash",
       "ii": 37.9
     },
+    {
+      "id": "kimi-k2.7-code",
+      "ii": 25.8
+    },
     {
       "id": "longcat-2.0",
       "ii": 19.1
     },
     {
-      "id": "step-5-preview",
-      "ii": 43.7
+      "id": "minimax-m3.1-flash",
+      "ii": 42.7
+    },
+    {
+      "id": "claude-haiku-5-5",
+      "ii": 43.4
+    },
+    {
+      "id": "longcat-2.5-preview-free",
+      "ii": null
+    },
+    {
+      "id": "grok-4.7",
+      "ii": 46.4
+    },
+    {
+      "id": "mimo-v2.5-pro",
+      "ii": 26
+    },
+    {
+      "id": "space-bunny",
+      "ii": null
+    },
+    {
+      "id": "kimi-k3",
+      "ii": 43.6
+    },
+    {
+      "id": "minimax-m3.1-flash-free",
+      "ii": 42.7
+    },
+    {
+      "id": "minimax-m2.7",
+      "ii": 22.8
+    },
+    {
+      "id": "iceman-contributor-free",
+      "ii": null
+    },
+    {
+      "id": "beam-free",
+      "ii": 30.3
+    },
+    {
+      "id": "deepseek-v4-pro",
+      "ii": 36
+    },
+    {
+      "id": "muse-spark-1.2-contributor",
+      "ii": 39.6
     }
   ],
-  "newModels": [],
+  "newModels": [
+    "kimi-k3.1-pro",
+    "gemini-4-argon",
+    "minimax-m3.1-flash",
+    "iceman-contributor-free"
+  ],
   "removedModels": [],
   "deltas": [],
-  "liveCatalogSize": 37,
+  "liveCatalogSize": 38,
   "notInLiveCatalog": [
+    "cat-jam-free",
+    "gemini-4-argon-contributor",
     "step-5-preview-free",
+    "longcat-2.5-preview-free",
     "space-bunny",
-    "cat-jam-free"
+    "minimax-m3.1-flash-free"
   ]
 }