Track week-over-week movement in the Intelligence Index
Deploy to Cloudflare Pages / deploy (push) Successful in 36s

- sync-catalog keeps a rolling 52-week history of index scores
- the matrix shows the delta since the previous refresh plus a biggest-mover card
This commit is contained in:
2026-10-21 17:14:52 +00:00
parent 57e9cdf4cc
commit 99489ca17b
8 changed files with 1258 additions and 1143 deletions
+25 -3
View File
@@ -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 $" + bestValue.blend.toFixed(2) + "/1M"],
["Free tier", MODELS.filter((m) => m.free).length, "limited-time free models"],
["Data snapshot", snapshotDate, "refreshed weekly by CI"]
["Data snapshot", snapshotDate, "refreshed weekly by CI"],
["Biggest movers", movers.length ? movers[0].name : "—", movers.length ? "index " + (movers[0].delta > 0 ? "+" : "") + movers[0].delta + " this week" : "no changes vs last run"]
].map(([k, v, s]) => `<div class="card"><div class="k">${k}</div><div class="v">${v}</div><div class="sub" style="font-size:11px">${s}</div></div>`).join("");
/* ---------- matrix --------------------------------------------------------- */
@@ -127,7 +147,9 @@ function renderMatrix() {
if (c.key === "name") return;
const v = c.get(m);
if (c.key === "ii") {
h += `<td><div class="cell" style="background:${v === null ? "transparent" : "#1b2233"}">${v === null ? '<span class="na">n/a</span>' : `<b>${v.toFixed(1)}</b>`}</div></td>`;
const d = DELTA[m.id];
const dTxt = d ? `<span style="color:${d > 0 ? "#57cc8a" : "#f2857f"}">${d > 0 ? "▲" : "▼"}${Math.abs(d).toFixed(1)}</span>` : "";
h += `<td><div class="cell" style="background:${v === null ? "transparent" : "#1b2233"}">${v === null ? '<span class="na">n/a</span>' : `<b>${v.toFixed(1)}</b> ${dTxt}`}</div></td>`;
return;
}
if (c.key === "blend") { h += `<td class="price">${m.free ? "$0" : "$" + v.toFixed(2)}</td>`; 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.<br>
• 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.<br><br>
Sources: <a href="https://artificialanalysis.ai">Artificial Analysis</a> (benchmarks, Intelligence Index), <a href="https://models.dev">models.dev</a> (Go catalogue, pricing, context, modalities), <a href="https://opencode.ai/data">OpenCode Data</a> (usage and retention) and the <a href="https://opencode.ai/docs/go">OpenCode Go docs</a> (allowances, privacy). Vendor announcements for model positioning.<br>
Data snapshot: <b>${snapshotDate || "n/a"}</b> — refreshed weekly by the <code>weekly-eval.yml</code> workflow.`;
Data snapshot: <b>${snapshotDate || "n/a"}</b> — refreshed weekly by the <code>weekly-eval.yml</code> workflow. The ▲/▼ marker in the Index column is the change since the previous weekly refresh.${HISTORY.length > 1 ? ` ${HISTORY.length} weekly snapshots recorded.` : ""}`;
+335 -335
View File
@@ -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"
]
};
+647 -647
View File
File diff suppressed because it is too large Load Diff
+37
View File
@@ -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
}
}
];
+35
View File
@@ -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
}
}
]
+127 -127
View File
@@ -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"
]
}