Automate the evaluation on a weekly schedule
Deploy to Cloudflare Pages / deploy (push) Successful in 30s
Deploy to Cloudflare Pages / deploy (push) Successful in 30s
- scripts/sync-catalog.mjs: rebuilds the Go catalogue from models.dev and benchmark scores from Artificial Analysis, and records what changed in snapshot.json - scripts/build-models-md.mjs: regenerates MODELS.md from the data layers - scripts/notify-new-models.mjs: files an issue when a new model needs a write-up - weekly-eval.yml: cron every Monday 05:23 UTC -> refresh -> commit -> Pages deploy - site now renders every model in the catalogue (33) with a data-snapshot stamp; auto-added models are flagged 'no write-up' until described - replaced scripts/refresh-evals.mjs with the wider sync script
This commit is contained in:
+65
-38
@@ -1,7 +1,34 @@
|
||||
import { CATALOG, SNAPSHOT } from "./catalog.js";
|
||||
import { RAW } from "./evals.js";
|
||||
import { GO_MODELS, FREE_NOTES, CATEGORIES } from "./data.js";
|
||||
import { GO_MODELS, FREE_NOTES } from "./data.js";
|
||||
|
||||
/* ---------- shared helpers ---------- */
|
||||
/* ---------- merge the three layers -----------------------------------------
|
||||
catalog.js auto-generated — every model currently in OpenCode Go
|
||||
evals.js auto-generated — benchmark scores per model
|
||||
data.js hand-written — what each model is targeted for
|
||||
--------------------------------------------------------------------------- */
|
||||
const DESC = Object.fromEntries(GO_MODELS.map((m) => [m.id, m]));
|
||||
const SCORES = Object.fromEntries(RAW.map((m) => [m.id, m]));
|
||||
|
||||
const MODELS = CATALOG.map((c) => {
|
||||
const d = DESC[c.id] || {};
|
||||
const s = SCORES[c.id] || {};
|
||||
const m = {
|
||||
...c,
|
||||
best: d.best || [],
|
||||
blurb: d.blurb || c.description || "No description published yet.",
|
||||
target: d.target || "",
|
||||
caveats: d.caveats || [],
|
||||
written: !!d.blurb,
|
||||
ii: s.ii ?? null,
|
||||
tasks: {},
|
||||
src: {}
|
||||
};
|
||||
m.blend = m.free ? 0 : 0.7 * m.price.in + 0.3 * m.price.out;
|
||||
return m;
|
||||
});
|
||||
|
||||
/* ---------- shared helpers ------------------------------------------------ */
|
||||
const el = (id) => document.getElementById(id);
|
||||
const tip = el("tip");
|
||||
function showTip(html, e) {
|
||||
@@ -40,32 +67,31 @@ const TASKS = [
|
||||
{ key: "pro", label: "Professional work", picks: [["gdpv", "GDPval-AA"], ["gdppdf", "GDP-PDF"]] }
|
||||
];
|
||||
|
||||
RAW.forEach((m) => {
|
||||
m.tasks = {}; m.src = {};
|
||||
MODELS.forEach((m) => {
|
||||
TASKS.forEach((t) => {
|
||||
for (const [f, label] of t.picks) {
|
||||
const v = m[f];
|
||||
const v = SCORES[m.id]?.[f];
|
||||
if (v !== null && v !== undefined) { m.tasks[t.key] = v; m.src[t.key] = label; break; }
|
||||
}
|
||||
});
|
||||
m.blend = m.free ? 0 : 0.7 * m.pi + 0.3 * m.po;
|
||||
});
|
||||
|
||||
const byId = Object.fromEntries(RAW.map((m) => [m.id, m]));
|
||||
|
||||
/* ---------- header cards ---------- */
|
||||
const scored = RAW.filter((m) => m.ii !== null);
|
||||
const scored = MODELS.filter((m) => m.ii !== null);
|
||||
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);
|
||||
|
||||
/* ---------- header cards -------------------------------------------------- */
|
||||
el("cards").innerHTML = [
|
||||
["Models in Go", RAW.length, "in the Go catalog"],
|
||||
["Models in Go", MODELS.length, "in the OpenCode Go catalogue"],
|
||||
["With public evals", scored.length, "Artificial Analysis harness"],
|
||||
["Top overall", topOverall.n, "index " + topOverall.ii.toFixed(1)],
|
||||
["Best value", bestValue.n, "index " + bestValue.ii.toFixed(1) + " at $" + bestValue.blend.toFixed(2) + "/1M"],
|
||||
["Free tier", RAW.filter((m) => m.free).length, "limited-time free models"]
|
||||
["Free tier", MODELS.filter((m) => m.free).length, "limited-time free models"],
|
||||
["Data snapshot", snapshotDate, "refreshed weekly by CI"]
|
||||
].map(([k, v, s]) => `<div class="card"><div class="k">${k}</div><div class="v">${v}</div><div class="sub" style="font-size:11px">${s}</div></div>`).join("");
|
||||
|
||||
/* ---------- matrix ---------- */
|
||||
/* ---------- matrix --------------------------------------------------------- */
|
||||
const cols = [
|
||||
{ key: "name", label: "Model", get: (m) => m.n, txt: true },
|
||||
{ key: "ii", label: "Index", get: (m) => m.ii },
|
||||
@@ -78,10 +104,10 @@ function renderMatrix() {
|
||||
const best = {};
|
||||
cols.forEach((c) => {
|
||||
if (c.key === "name" || c.key === "blend") return;
|
||||
const vals = RAW.map((m) => c.get(m)).filter((v) => v !== null && v !== undefined);
|
||||
const vals = MODELS.map((m) => c.get(m)).filter((v) => v !== null && v !== undefined);
|
||||
best[c.key] = vals.length ? Math.max(...vals) : null;
|
||||
});
|
||||
const rows = RAW.slice().sort((a, b) => {
|
||||
const rows = MODELS.slice().sort((a, b) => {
|
||||
const c = cols.find((x) => x.key === sortKey);
|
||||
const va = c.get(a), vb = c.get(b);
|
||||
if (sortKey === "name") return String(va).localeCompare(String(vb)) * sortDir;
|
||||
@@ -95,7 +121,8 @@ function renderMatrix() {
|
||||
});
|
||||
h += "</tr></thead><tbody>";
|
||||
rows.forEach((m) => {
|
||||
h += `<tr><td class="name">${m.n}${m.free ? '<span class="tag free">free</span>' : ""}<div class="price">${m.lab} · $${m.pi}/${m.po} · ${(m.ctx / 1e6).toFixed(m.ctx % 1e6 ? 2 : 0)}M ctx${m.ii === null ? " · no public evals" : ""}</div></td>`;
|
||||
const ctx = m.ctx ? `${(m.ctx / 1e6).toFixed(m.ctx % 1e6 ? 2 : 0)}M ctx` : "ctx n/a";
|
||||
h += `<tr><td class="name">${m.n}${m.free ? '<span class="tag free">free</span>' : ""}${!m.written ? '<span class="tag warn">no write-up</span>' : ""}<div class="price">${m.lab || "—"} · $${m.price.in}/${m.price.out} · ${ctx}${m.ii === null ? " · no public evals" : ""}</div></td>`;
|
||||
cols.forEach((c) => {
|
||||
if (c.key === "name") return;
|
||||
const v = c.get(m);
|
||||
@@ -127,7 +154,7 @@ function renderMatrix() {
|
||||
}
|
||||
renderMatrix();
|
||||
|
||||
/* ---------- svg helpers ---------- */
|
||||
/* ---------- svg helpers ---------------------------------------------------- */
|
||||
function svgEl(tag, attrs, parent) {
|
||||
const e = document.createElementNS("http://www.w3.org/2000/svg", tag);
|
||||
for (const k in attrs) e.setAttribute(k, attrs[k]);
|
||||
@@ -135,12 +162,12 @@ function svgEl(tag, attrs, parent) {
|
||||
return e;
|
||||
}
|
||||
|
||||
/* ---------- scatter ---------- */
|
||||
/* ---------- scatter -------------------------------------------------------- */
|
||||
(function scatter() {
|
||||
const box = el("scatter"); box.innerHTML = "";
|
||||
const W = 520, H = 340, m = { l: 52, r: 16, t: 16, b: 44 };
|
||||
const svg = svgEl("svg", { viewBox: `0 0 ${W} ${H}`, width: "100%", height: "auto" }, box);
|
||||
const pts = scored.filter((x) => x.ii !== null);
|
||||
const pts = scored.filter((x) => x.ii !== null && x.blend > 0);
|
||||
const maxX = Math.max(...pts.map((p) => p.blend)) * 1.1 || 1, maxY = 60;
|
||||
const X = (v) => m.l + (v / maxX) * (W - m.l - m.r);
|
||||
const Y = (v) => H - m.b - (v / maxY) * (H - m.t - m.b);
|
||||
@@ -158,21 +185,21 @@ function svgEl(tag, attrs, parent) {
|
||||
const c = svgEl("circle", { cx: X(p.blend), cy: Y(p.ii), r: 5, fill: p.free ? "#2ecc71" : "#7cc4ff", "fill-opacity": 0.85, stroke: "#0b0d12", "stroke-width": 1.5 }, svg);
|
||||
const lbl = svgEl("text", { x: X(p.blend) + 8, y: Y(p.ii) + 3, fill: "#c8cede", "font-size": 10 }, svg);
|
||||
lbl.textContent = p.n.length > 22 ? p.n.slice(0, 21) + "…" : p.n;
|
||||
c.onmousemove = (e) => showTip(`<b>${p.n}</b><br>Index ${p.ii.toFixed(1)}<br>${p.free ? "Free" : `$${p.pi} in / $${p.po} out per 1M`}`, e);
|
||||
c.onmousemove = (e) => showTip(`<b>${p.n}</b><br>Index ${p.ii.toFixed(1)}<br>${p.free ? "Free" : `$${p.price.in} in / $${p.price.out} out per 1M`}`, e);
|
||||
c.onmouseleave = hideTip;
|
||||
});
|
||||
})();
|
||||
|
||||
/* ---------- value ranking ---------- */
|
||||
/* ---------- value ranking -------------------------------------------------- */
|
||||
(function valueChart() {
|
||||
const box = el("value"); box.innerHTML = "";
|
||||
const W = 520, H = 340, m = { l: 96, r: 16, t: 12, b: 28 };
|
||||
const svg = svgEl("svg", { viewBox: `0 0 ${W} ${H}`, width: "100%", height: "auto" }, box);
|
||||
const pts = scored.filter((p) => !p.free).map((p) => ({ ...p, v: p.ii / p.blend })).sort((a, b) => b.v - a.v);
|
||||
const pts = scored.filter((p) => !p.free && p.blend > 0).map((p) => ({ ...p, v: p.ii / p.blend })).sort((a, b) => b.v - a.v);
|
||||
const maxV = Math.max(...pts.map((p) => p.v)) * 1.08;
|
||||
const step = (H - m.t - m.b) / Math.max(pts.length, 1);
|
||||
pts.forEach((p, i) => {
|
||||
const y = 26 + i * step;
|
||||
const y = 22 + i * step;
|
||||
const w = Math.max(2, (p.v / maxV) * (W - m.l - m.r));
|
||||
svgEl("rect", { x: m.l, y: y - 9, width: w, height: 15, rx: 3, fill: "#7cc4ff", "fill-opacity": 0.85 }, svg);
|
||||
svgEl("text", { x: m.l - 8, y: y + 3, fill: "#c8cede", "font-size": 11, "text-anchor": "end" }, svg).textContent = p.n.length > 17 ? p.n.slice(0, 16) + "…" : p.n;
|
||||
@@ -182,26 +209,25 @@ function svgEl(tag, attrs, parent) {
|
||||
svgEl("text", { x: m.l, y: H - 6, fill: "#2ecc71", "font-size": 11 }, svg).textContent = "Free models (not ranked): " + free.map((f) => f.n).join(", ");
|
||||
})();
|
||||
|
||||
/* ---------- model guide ---------- */
|
||||
/* ---------- model guide ---------------------------------------------------- */
|
||||
function modelCard(m) {
|
||||
const tags = (m.best || []).map((b) => {
|
||||
const key = Object.keys(CATEGORIES).find((k) => CATEGORIES[k].label.toLowerCase() === b.toLowerCase());
|
||||
const key = b === "Free tier" ? "free" : b === "Image generation" ? "imagegen" : "";
|
||||
const cls = key === "free" ? "tag free" : key === "imagegen" ? "tag warn" : "tag";
|
||||
return `<span class="${cls}">${b}</span>`;
|
||||
}).join("");
|
||||
const ev = byId[m.id];
|
||||
const idx = ev && ev.ii !== null ? `index ${ev.ii.toFixed(1)}` : "no public evals";
|
||||
const idx = m.ii !== null ? `index ${m.ii.toFixed(1)}` : "no public evals";
|
||||
const ctx = m.ctx ? `${(m.ctx / 1e6).toFixed(m.ctx % 1e6 ? 2 : 0)}M context` : "context n/a";
|
||||
return `<div class="card2">
|
||||
<div class="hd"><h3>${m.name}</h3><span class="lab">${m.lab}</span></div>
|
||||
<div class="meta">released ${m.released} · $${m.price.in}/${m.price.out} per 1M · ${m.ctx} context · ${m.modalities} · ${idx}</div>
|
||||
<div class="hd"><h3>${m.n}</h3><span class="lab">${m.lab || "undisclosed"}</span></div>
|
||||
<div class="meta">released ${m.released || "?"} · $${m.price.in}/${m.price.out} per 1M · ${ctx} · ${m.modalities} · ${idx}</div>
|
||||
<div>${tags}</div>
|
||||
<p class="blurb">${m.blurb}</p>
|
||||
<p><b>Targeted for:</b> ${m.target}</p>
|
||||
${m.target ? `<p><b>Targeted for:</b> ${m.target}</p>` : `<p><i>No write-up yet — this model was added to the catalogue automatically and needs a description.</i></p>`}
|
||||
${m.caveats && m.caveats.length ? `<div class="caveats"><b>Caveats</b><ul>${m.caveats.map((c) => `<li>${c}</li>`).join("")}</ul></div>` : ""}
|
||||
</div>`;
|
||||
}
|
||||
|
||||
// loose keyword matching so a model's plain-language tags still hit the right filter
|
||||
const FILTER_WORDS = {
|
||||
agentic: ["agent"],
|
||||
coding: ["cod", "repo"],
|
||||
@@ -213,17 +239,17 @@ const FILTER_WORDS = {
|
||||
};
|
||||
|
||||
function renderGuide(filter) {
|
||||
const list = GO_MODELS.filter((m) => {
|
||||
const list = MODELS.filter((m) => {
|
||||
if (!filter || filter === "all") return true;
|
||||
if (filter === "free") return m.free;
|
||||
if (filter === "new") return m.released >= "2026-08-01";
|
||||
if (filter === "new") return (m.released || "") >= "2026-08-01";
|
||||
const words = FILTER_WORDS[filter] || [];
|
||||
const hay = m.best.join(" ").toLowerCase();
|
||||
return words.some((w) => hay.includes(w));
|
||||
});
|
||||
const extra = filter === "all" || filter === "free" ? `
|
||||
<div class="note"><b>Also free outside the Go plan</b><br>${FREE_NOTES.map((f) => `<b>${f.name}</b> (${f.lab}, ${f.where}) — ${f.target} <i>${f.note}</i>`).join("<br>")}</div>` : "";
|
||||
const none = list.length ? "" : `<div class="note">No model in the Go catalog matches this category. Every Go model is text-output — none of them generate images, so image generation needs a different provider.</div>`;
|
||||
const none = list.length ? "" : `<div class="note">No model in the Go catalogue matches this category. Every Go model is text-output — none of them generate images, so image generation needs a different provider.</div>`;
|
||||
el("guide").innerHTML = list.map(modelCard).join("") + extra + none;
|
||||
}
|
||||
|
||||
@@ -249,7 +275,8 @@ el("foot").innerHTML = `
|
||||
• Terminal-agent, tool-use, science and professional-work columns fall back to a second benchmark when a model has not been run on the first (Terminal-Bench 2.1 → 4.0 → Hard; τ²-bench → τ-bench Banking; GPQA → CritPt; GDPval → GDP-PDF). Scores are comparable within a column, but the underlying benchmark can differ per row — hover to check.<br>
|
||||
• "Index" is the Artificial Analysis Intelligence Index, a weighted composite of those evaluations.<br>
|
||||
• Prices are OpenCode Go list prices per 1M tokens (input/output). Blended price = 70% input / 30% output.<br>
|
||||
• Free-tier models (MiniMax M3.1 Flash Free, Beam Free, LongCat 2.5 Preview Free) are limited-time offers with unlimited included usage.<br>
|
||||
• Hy4 preview and LongCat 2.5 Preview Free have no public third-party evaluations yet, so they show as "n/a". Qwen3.8 Flash maps to Artificial Analysis' "Qwen3.8-Flash-Next" entry.<br>
|
||||
• No model in the Go catalog generates images — all Go models are text-output. "Image understanding" rows mean 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://opencode.ai/data">OpenCode Data</a> (catalog, usage, context windows) and <a href="https://opencode.ai/docs/go">OpenCode Go docs</a> (pricing, allowances, privacy). Vendor announcements for model positioning. Retrieved 2026-10-21.`;
|
||||
• Free-tier models are limited-time offers. Contributor-tier models (Gemini 4 Argon, Muse Spark) may use your prompts and completions for training.<br>
|
||||
• 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.`;
|
||||
|
||||
@@ -0,0 +1,545 @@
|
||||
// AUTO-GENERATED by scripts/sync-catalog.mjs — do not edit by hand.
|
||||
// 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",
|
||||
"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": "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": "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",
|
||||
"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": "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",
|
||||
"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": "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-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",
|
||||
"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
|
||||
},
|
||||
"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",
|
||||
"openWeights": true
|
||||
},
|
||||
{
|
||||
"id": "hy4-preview",
|
||||
"n": "Hy4 preview",
|
||||
"lab": "tencent",
|
||||
"released": "2026-08-28",
|
||||
"price": {
|
||||
"in": 0.834,
|
||||
"out": 2.501
|
||||
},
|
||||
"free": false,
|
||||
"ctx": 1024000,
|
||||
"modalities": "text in → text out",
|
||||
"description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.",
|
||||
"canonical": "tencent/hy4-preview",
|
||||
"openWeights": true
|
||||
},
|
||||
{
|
||||
"id": "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": "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",
|
||||
"released": "2026-08-26",
|
||||
"price": {
|
||||
"in": 0.15,
|
||||
"out": 0.5
|
||||
},
|
||||
"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
|
||||
},
|
||||
{
|
||||
"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": "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",
|
||||
"n": "MiMo V2.5",
|
||||
"lab": "xiaomi",
|
||||
"released": "2026-04-22",
|
||||
"price": {
|
||||
"in": 0.14,
|
||||
"out": 0.28
|
||||
},
|
||||
"free": false,
|
||||
"ctx": 1000000,
|
||||
"modalities": "text, image, audio, video in → text out",
|
||||
"description": "MiMo omni model for text, image, video, audio, and agents",
|
||||
"canonical": "xiaomi/mimo-v2.5",
|
||||
"openWeights": true
|
||||
},
|
||||
{
|
||||
"id": "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": "glm-5.3",
|
||||
"n": "GLM-5.3",
|
||||
"lab": "zhipuai",
|
||||
"released": "2026-08-14",
|
||||
"price": {
|
||||
"in": 1.4,
|
||||
"out": 4.4
|
||||
},
|
||||
"free": false,
|
||||
"ctx": 1000000,
|
||||
"modalities": "text in → text out",
|
||||
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
|
||||
"canonical": "zhipuai/glm-5.3",
|
||||
"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": "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": "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
|
||||
}
|
||||
];
|
||||
|
||||
export const SNAPSHOT = {
|
||||
"generated": "2026-10-21T17:03:04.948Z",
|
||||
"models": 33,
|
||||
"newModels": [],
|
||||
"removedModels": [],
|
||||
"deltas": [],
|
||||
"notInLiveCatalog": [
|
||||
"step-5-preview-free",
|
||||
"cat-jam-free",
|
||||
"space-bunny"
|
||||
]
|
||||
};
|
||||
@@ -368,6 +368,158 @@ export const GO_MODELS = [
|
||||
target:
|
||||
"Repo-scale SWE work with perception in the loop: MiniMax reports one of the strongest SWE-Bench Verified results in Go, plus good browser and desktop-computer scores (BrowseComp, MCP Atlas, OSWorld). Use it when the agent has to look at a screen and then change code.",
|
||||
caveats: ["Text output only.", "Weaker than MiniMax M3.1 Flash on frontier reasoning and long-horizon tasks."]
|
||||
},
|
||||
{
|
||||
id: "gpt-5.6-luna",
|
||||
name: "GPT-5.6 Luna",
|
||||
lab: "OpenAI",
|
||||
released: "2026-06-01",
|
||||
price: { in: 0.2, out: 1.2 },
|
||||
ctx: "1.05M",
|
||||
modalities: "text, image, PDF in → text out",
|
||||
best: ["Fast & cheap", "High-volume coding", "Agents"],
|
||||
blurb:
|
||||
"Cost-efficient GPT-5.6 model for fast, high-volume workloads.",
|
||||
target:
|
||||
"Throughput work: many small calls, classification, extraction, routing and repetitive edits where latency and cost per call decide the outcome. Keeps the GPT tool-calling behaviour at roughly twice the price of GPT-6 Luna.",
|
||||
caveats: ["Price steps up above 272K tokens of context."]
|
||||
},
|
||||
{
|
||||
id: "muse-spark-1.2-contributor",
|
||||
name: "Muse Spark 1.2 Contributor",
|
||||
lab: "Meta",
|
||||
released: "2026-08-01",
|
||||
price: { in: 0.1, out: 0.2 },
|
||||
ctx: "1M",
|
||||
modalities: "text, image, video, PDF, audio in → text out",
|
||||
best: ["Coding", "Multimodal", "Cheap"],
|
||||
blurb:
|
||||
"Coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.",
|
||||
target:
|
||||
"The previous Muse generation — kept in Go because it is cheap and coding-focused. Pick it when you want Meta's multimodal input surface at $0.10/$0.20 and 1.3 is not required; otherwise use Muse Spark 1.3.",
|
||||
caveats: ["Contributor tier — prompts and completions may be used to train future Meta models.", "Superseded by Muse Spark 1.3 on long-horizon agent tasks."]
|
||||
},
|
||||
{
|
||||
id: "glm-5.2",
|
||||
name: "GLM-5.2",
|
||||
lab: "Zhipu",
|
||||
released: "2026-06-01",
|
||||
price: { in: 1.4, out: 4.4 },
|
||||
ctx: "1M",
|
||||
modalities: "text only",
|
||||
best: ["Long-horizon coding", "Agents", "Math & science"],
|
||||
blurb:
|
||||
"Open flagship GLM for long-horizon coding agents and million-token context work.",
|
||||
target:
|
||||
"The GLM generation before 5.3: still strong on long-horizon coding agents with a million-token window, and its AIME/HMMT/IMO scores make it the maths-and-science option in the family. GLM-5.3 is the better default where budget allows.",
|
||||
caveats: ["Text input only.", "Expensive per token ($1.40 / $4.40)."]
|
||||
},
|
||||
{
|
||||
id: "hy3",
|
||||
name: "Hy3",
|
||||
lab: "Tencent",
|
||||
released: "2026-04-01",
|
||||
price: { in: 0.14, out: 0.58 },
|
||||
ctx: "256K",
|
||||
modalities: "text only",
|
||||
best: ["Cheap", "Reasoning", "Instruction following", "Tool use"],
|
||||
blurb:
|
||||
"Tencent Hy reasoning model for coding, instruction following, and agent tasks.",
|
||||
target:
|
||||
"A cheap reasoning model with unusually strong instruction following (IFBench) and tool use (τ-bench) for its price. Suited to spec-driven agents and short coding loops; the 256K window is the main limitation for repo-scale work.",
|
||||
caveats: ["256K context.", "Text input only."]
|
||||
},
|
||||
{
|
||||
id: "mimo-v2.6-flash",
|
||||
name: "MiMo-V2.6-Flash",
|
||||
lab: "Xiaomi",
|
||||
released: "2026-09-22",
|
||||
price: { in: 0.14, out: 0.28 },
|
||||
ctx: "1M",
|
||||
modalities: "text, image, audio, video in → text out",
|
||||
best: ["Cheap", "Multimodal", "Automation", "Coding agents"],
|
||||
blurb:
|
||||
"MiMo Flash model for multimodal coding agents and long-context automation.",
|
||||
target:
|
||||
"The cheapest multimodal agent in Go at 14¢/28¢ per 1M: bulk automation over long contexts, agents that must read images, video or audio, and the majority of mechanical coding-agent traffic.",
|
||||
caveats: ["Text output only.", "Noticeably weaker than MiMo-V2.6-Pro on hard agentic and security tasks."]
|
||||
},
|
||||
{
|
||||
id: "minimax-m2.7",
|
||||
name: "MiniMax M2.7",
|
||||
lab: "MiniMax",
|
||||
released: "2026-05-01",
|
||||
price: { in: 0.3, out: 1.2 },
|
||||
ctx: "200K",
|
||||
modalities: "text only",
|
||||
best: ["Coding", "Office work", "Agentic tasks"],
|
||||
blurb:
|
||||
"MiniMax model for chat, coding, office work, and agentic tasks.",
|
||||
target:
|
||||
"The generation before MiniMax M3: general chat plus coding and office deliverables. Cheap, but the 200K window and older agentic scores make it a fallback now that M3 and M3.1 Flash exist.",
|
||||
caveats: ["200K context — the smallest window in the Go catalogue.", "Superseded by MiniMax M3."]
|
||||
},
|
||||
{
|
||||
id: "longcat-2.0",
|
||||
name: "LongCat-2.0",
|
||||
lab: "Meituan",
|
||||
released: "2026-06-29",
|
||||
price: { in: 0.3, out: 1.2 },
|
||||
ctx: "1M",
|
||||
modalities: "text only",
|
||||
best: ["Coding", "Reasoning", "Long context", "Open weights"],
|
||||
blurb:
|
||||
"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window.",
|
||||
target:
|
||||
"Long-context reasoning with tool calling at a modest price — useful for repo-scale analysis and document-heavy agent loops. Text-only, so perception work needs the 2.5 preview.",
|
||||
caveats: ["Text input only.", "Superseded by LongCat 2.5 Preview, which adds image input."]
|
||||
},
|
||||
{
|
||||
id: "step-5-preview-free",
|
||||
name: "Step 5 Preview Free",
|
||||
lab: "StepFun",
|
||||
released: "2026-09-16",
|
||||
price: { in: 0, out: 0 },
|
||||
free: true,
|
||||
ctx: "1M",
|
||||
modalities: "text, image, video in → text out",
|
||||
best: ["Free tier", "Coding", "Professional knowledge work", "Multimodal"],
|
||||
blurb:
|
||||
"Free access to StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image and video input and a 1M-token context window.",
|
||||
target:
|
||||
"Same model as the paid Step 5 Preview, without the token bill — useful for long agent runs and multimodal work while the paid allowance is reserved for the hard tasks.",
|
||||
caveats: ["Limited-time free entry; not present in the live Go catalogue endpoint, so availability may vary."]
|
||||
},
|
||||
{
|
||||
id: "cat-jam-free",
|
||||
name: "cat-jam-free",
|
||||
lab: "Undisclosed",
|
||||
released: "2026-10-01",
|
||||
price: { in: 0, out: 0 },
|
||||
free: true,
|
||||
ctx: "1M",
|
||||
modalities: "text only",
|
||||
best: ["Free tier", "Coding", "Agentic workflows", "Structured output"],
|
||||
blurb:
|
||||
"A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.",
|
||||
target:
|
||||
"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.",
|
||||
caveats: ["No vendor, no model card, no public evaluation — verify behaviour before depending on it.", "Not listed in the live Go catalogue endpoint."]
|
||||
},
|
||||
{
|
||||
id: "space-bunny",
|
||||
name: "space-bunny",
|
||||
lab: "Undisclosed",
|
||||
released: "2026-10-01",
|
||||
price: { in: 0.15, out: 0.6 },
|
||||
ctx: "1M",
|
||||
modalities: "text, image, video in → text out",
|
||||
best: ["Coding", "Agentic tasks", "Tool use", "Multimodal"],
|
||||
blurb:
|
||||
"Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input.",
|
||||
target:
|
||||
"An unreleased preview model with full multimodal input and tool use, priced like the value tier. It has no vendor behind it and no public evaluation, so treat it as an experiment rather than a recommendation.",
|
||||
caveats: ["No vendor or model card — no published evaluation.", "Not listed in the live Go catalogue endpoint."]
|
||||
}
|
||||
];
|
||||
|
||||
|
||||
+926
-25
@@ -1,27 +1,928 @@
|
||||
// Evaluation data scraped from Artificial Analysis model pages (single consistent harness).
|
||||
// Values are already scaled to 0-100. Regenerate with: node scripts/refresh-evals.mjs
|
||||
// AUTO-GENERATED by scripts/sync-catalog.mjs — do not edit by hand.
|
||||
// Benchmark scores from Artificial Analysis (single consistent harness), scaled to 0-100.
|
||||
export const RAW = [
|
||||
{"id":"minimax-m3.1-flash-free","n":"MiniMax M3.1 Flash Free","lab":"MiniMax","free":true,"pi":0,"po":0,"ii":42.7,"fc":38.6,"scicode":53.4,"tb21":null,"tb40":25.8,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":null,"auto":72.5,"gpqa":null,"critpt":22.3,"hle":48,"lcr":79.7,"ifbench":null,"mmmu":79.1,"gdpv":47.9,"gdppdf":20.8,"ctx":1000000},
|
||||
{"id":"gemini-4-argon-contributor","n":"Gemini 4 Argon Contributor","lab":"Google","free":false,"pi":4,"po":20,"ii":52.6,"fc":43.5,"scicode":61.8,"tb21":null,"tb40":57.1,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":48.8,"auto":77.5,"gpqa":null,"critpt":27.1,"hle":57.1,"lcr":79.7,"ifbench":null,"mmmu":null,"gdpv":56.2,"gdppdf":21.8,"ctx":1048576},
|
||||
{"id":"claude-haiku-5-5","n":"Claude Haiku 5.5","lab":"Anthropic","free":false,"pi":0.1,"po":0.5,"ii":43.4,"fc":41.8,"scicode":55,"tb21":null,"tb40":32.8,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":53.8,"auto":35.4,"gpqa":null,"critpt":18.9,"hle":44.4,"lcr":82.7,"ifbench":null,"mmmu":null,"gdpv":55.9,"gdppdf":20.8,"ctx":1000000},
|
||||
{"id":"beam-free","n":"Beam Free","lab":"Reflection AI","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":"longcat-2.5-preview-free","n":"LongCat 2.5 Preview Free","lab":"Meituan","free":true,"pi":0,"po":0,"ii":null,"fc":null,"scicode":null,"tb21":null,"tb40":null,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":null,"auto":null,"gpqa":null,"critpt":null,"hle":null,"lcr":null,"ifbench":null,"mmmu":null,"gdpv":null,"gdppdf":null,"ctx":1000000},
|
||||
{"id":"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,"tb21":null,"tb40":34.8,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":37.5,"auto":58.6,"gpqa":null,"critpt":26.6,"hle":49.4,"lcr":86.3,"ifbench":null,"mmmu":null,"gdpv":59.2,"gdppdf":19.2,"ctx":1048576},
|
||||
{"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":46.6,"gdppdf":22.8,"ctx":1050000},
|
||||
{"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":"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},
|
||||
{"id":"deepseek-v4.1-flash","n":"DeepSeek V4.1 Flash","lab":"DeepSeek","free":false,"pi":0.15,"po":0.6,"ii":39.5,"fc":44,"scicode":51.9,"tb21":null,"tb40":26.8,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":35,"auto":68.9,"gpqa":null,"critpt":14.3,"hle":39.2,"lcr":84,"ifbench":null,"mmmu":77,"gdpv":55,"gdppdf":12.8,"ctx":1000000},
|
||||
{"id":"muse-spark-1.3-contributor","n":"Muse Spark 1.3 Contributor","lab":"Meta","free":false,"pi":0.1,"po":0.2,"ii":48.1,"fc":40.6,"scicode":58.8,"tb21":84.3,"tb40":33.3,"tbh":null,"tau2":null,"taub":50.5,"apex":null,"analyst":37.5,"auto":57.9,"gpqa":93.5,"critpt":24.9,"hle":48.7,"lcr":83,"ifbench":null,"mmmu":null,"gdpv":59,"gdppdf":26.6,"ctx":1048576},
|
||||
{"id":"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":"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":"glm-5.3-flash","n":"GLM-5.3-Flash","lab":"Zhipu","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":"glm-5.3","n":"GLM-5.3","lab":"Zhipu","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":"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":"kimi-k3","n":"Kimi K3","lab":"Moonshot","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":"kimi-k2.7-code","n":"Kimi K2.7 Code","lab":"Moonshot","free":false,"pi":0.95,"po":4,"ii":25.8,"fc":null,"scicode":47.8,"tb21":67.4,"tb40":1,"tbh":44.7,"tau2":90.1,"taub":20.2,"apex":null,"analyst":null,"auto":24.5,"gpqa":89.6,"critpt":10,"hle":35,"lcr":79.3,"ifbench":63.1,"mmmu":null,"gdpv":26.9,"gdppdf":11.2,"ctx":262144},
|
||||
{"id":"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":"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":1048576},
|
||||
{"id":"deepseek-v4-pro","n":"DeepSeek V4 Pro","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":"mimo-v2.5-pro","n":"MiMo-V2.5-Pro","lab":"Xiaomi","free":false,"pi":0.435,"po":0.87,"ii":26,"fc":null,"scicode":50.6,"tb21":65.2,"tb40":0,"tbh":43.2,"tau2":94.2,"taub":9.9,"apex":2.4,"analyst":20,"auto":13.7,"gpqa":86.6,"critpt":4,"hle":35.7,"lcr":79.7,"ifbench":79.9,"mmmu":null,"gdpv":31,"gdppdf":4,"ctx":1048576},
|
||||
{"id":"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":24.9,"gdppdf":4,"ctx":1048576}
|
||||
{
|
||||
"id": "mimo-v2.5-pro",
|
||||
"n": "MiMo V2.5 Pro",
|
||||
"lab": "xiaomi",
|
||||
"free": false,
|
||||
"pi": 0.435,
|
||||
"po": 0.87,
|
||||
"ii": 26,
|
||||
"fc": null,
|
||||
"scicode": 50.6,
|
||||
"tb21": 65.2,
|
||||
"tb40": 0,
|
||||
"tbh": 43.2,
|
||||
"tau2": 94.2,
|
||||
"taub": 9.9,
|
||||
"apex": 2.4,
|
||||
"analyst": 20,
|
||||
"auto": 13.7,
|
||||
"gpqa": 86.6,
|
||||
"critpt": 4,
|
||||
"hle": 35.7,
|
||||
"lcr": 79.7,
|
||||
"ifbench": 79.9,
|
||||
"mmmu": null,
|
||||
"gdpv": 31,
|
||||
"gdppdf": 4,
|
||||
"ctx": 1048576
|
||||
},
|
||||
{
|
||||
"id": "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
|
||||
},
|
||||
{
|
||||
"id": "muse-spark-1.3-contributor",
|
||||
"n": "Muse Spark 1.3 Contributor",
|
||||
"lab": "meta",
|
||||
"free": false,
|
||||
"pi": 0.1,
|
||||
"po": 0.2,
|
||||
"ii": 48.1,
|
||||
"fc": 40.6,
|
||||
"scicode": 58.8,
|
||||
"tb21": 84.3,
|
||||
"tb40": 33.3,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": 50.5,
|
||||
"apex": null,
|
||||
"analyst": 37.5,
|
||||
"auto": 57.9,
|
||||
"gpqa": 93.5,
|
||||
"critpt": 24.9,
|
||||
"hle": 48.7,
|
||||
"lcr": 83,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": 59,
|
||||
"gdppdf": 26.6,
|
||||
"ctx": 1048576
|
||||
},
|
||||
{
|
||||
"id": "qwen3.8-flash",
|
||||
"n": "Qwen3.8 Flash",
|
||||
"lab": "alibaba",
|
||||
"free": false,
|
||||
"pi": 0.15,
|
||||
"po": 0.47,
|
||||
"ii": 39.8,
|
||||
"fc": null,
|
||||
"scicode": 50.6,
|
||||
"tb21": 86.1,
|
||||
"tb40": 25.3,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": 45.4,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": 55.9,
|
||||
"gpqa": 92.3,
|
||||
"critpt": 11.1,
|
||||
"hle": 38,
|
||||
"lcr": 79.7,
|
||||
"ifbench": null,
|
||||
"mmmu": 79.8,
|
||||
"gdpv": 56.4,
|
||||
"gdppdf": 15.6,
|
||||
"ctx": 1000000
|
||||
},
|
||||
{
|
||||
"id": "kimi-k3",
|
||||
"n": "Kimi K3",
|
||||
"lab": "moonshotai",
|
||||
"free": false,
|
||||
"pi": 3,
|
||||
"po": 15,
|
||||
"ii": 43.6,
|
||||
"fc": 43.6,
|
||||
"scicode": 59.5,
|
||||
"tb21": 85,
|
||||
"tb40": 12.6,
|
||||
"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": "deepseek-v4.1-flash",
|
||||
"n": "DeepSeek V4.1 Flash",
|
||||
"lab": "deepseek",
|
||||
"free": false,
|
||||
"pi": 0.15,
|
||||
"po": 0.6,
|
||||
"ii": 39.5,
|
||||
"fc": 44,
|
||||
"scicode": 51.9,
|
||||
"tb21": null,
|
||||
"tb40": 26.8,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": 35,
|
||||
"auto": 68.9,
|
||||
"gpqa": null,
|
||||
"critpt": 14.3,
|
||||
"hle": 39.2,
|
||||
"lcr": 84,
|
||||
"ifbench": null,
|
||||
"mmmu": 77,
|
||||
"gdpv": 55,
|
||||
"gdppdf": 12.8,
|
||||
"ctx": 1000000
|
||||
},
|
||||
{
|
||||
"id": "minimax-m2.7",
|
||||
"n": "MiniMax-M2.7",
|
||||
"lab": "minimax",
|
||||
"free": false,
|
||||
"pi": 0.3,
|
||||
"po": 1.2,
|
||||
"ii": 22.8,
|
||||
"fc": null,
|
||||
"scicode": 50.1,
|
||||
"tb21": 55.4,
|
||||
"tb40": 0,
|
||||
"tbh": 39.4,
|
||||
"tau2": 84.8,
|
||||
"taub": 9.9,
|
||||
"apex": 10.6,
|
||||
"analyst": 11.3,
|
||||
"auto": 4.4,
|
||||
"gpqa": 87.4,
|
||||
"critpt": 0.6,
|
||||
"hle": 29.6,
|
||||
"lcr": 78.3,
|
||||
"ifbench": 75.7,
|
||||
"mmmu": null,
|
||||
"gdpv": 25.5,
|
||||
"gdppdf": 6,
|
||||
"ctx": 204800
|
||||
},
|
||||
{
|
||||
"id": "minimax-m3.1-flash-free",
|
||||
"n": "MiniMax M3.1 Flash Free",
|
||||
"lab": "minimax",
|
||||
"free": true,
|
||||
"pi": 0,
|
||||
"po": 0,
|
||||
"ii": 42.7,
|
||||
"fc": 38.6,
|
||||
"scicode": 53.4,
|
||||
"tb21": null,
|
||||
"tb40": 25.8,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": 72.5,
|
||||
"gpqa": null,
|
||||
"critpt": 22.3,
|
||||
"hle": 48,
|
||||
"lcr": 79.7,
|
||||
"ifbench": null,
|
||||
"mmmu": 79.1,
|
||||
"gdpv": 47.9,
|
||||
"gdppdf": 20.8,
|
||||
"ctx": 1000000
|
||||
},
|
||||
{
|
||||
"id": "gemini-4-argon-contributor",
|
||||
"n": "Gemini 4 Argon Contributor",
|
||||
"lab": "google",
|
||||
"free": false,
|
||||
"pi": 4,
|
||||
"po": 20,
|
||||
"ii": 52.6,
|
||||
"fc": 43.5,
|
||||
"scicode": 61.8,
|
||||
"tb21": null,
|
||||
"tb40": 57.1,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": 48.8,
|
||||
"auto": 77.5,
|
||||
"gpqa": null,
|
||||
"critpt": 27.1,
|
||||
"hle": 57.1,
|
||||
"lcr": 79.7,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": 56.2,
|
||||
"gdppdf": 21.8,
|
||||
"ctx": 1048576
|
||||
},
|
||||
{
|
||||
"id": "qwen3.7-plus",
|
||||
"n": "Qwen3.7 Plus",
|
||||
"lab": "alibaba",
|
||||
"free": false,
|
||||
"pi": 0.4,
|
||||
"po": 1.6,
|
||||
"ii": 25.2,
|
||||
"fc": null,
|
||||
"scicode": 46.1,
|
||||
"tb21": 61,
|
||||
"tb40": 1,
|
||||
"tbh": 47,
|
||||
"tau2": 93,
|
||||
"taub": 17.5,
|
||||
"apex": 22.4,
|
||||
"analyst": null,
|
||||
"auto": 17.4,
|
||||
"gpqa": 90,
|
||||
"critpt": 9.1,
|
||||
"hle": 35.6,
|
||||
"lcr": 73,
|
||||
"ifbench": 78,
|
||||
"mmmu": 80.5,
|
||||
"gdpv": 13.4,
|
||||
"gdppdf": 12.2,
|
||||
"ctx": 1000000
|
||||
},
|
||||
{
|
||||
"id": "longcat-2.5-preview-free",
|
||||
"n": "LongCat 2.5 Preview Free",
|
||||
"lab": "meituan",
|
||||
"free": true,
|
||||
"pi": 0,
|
||||
"po": 0,
|
||||
"ii": null,
|
||||
"fc": null,
|
||||
"scicode": null,
|
||||
"tb21": null,
|
||||
"tb40": null,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": null,
|
||||
"gpqa": null,
|
||||
"critpt": null,
|
||||
"hle": null,
|
||||
"lcr": null,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": null,
|
||||
"gdppdf": null,
|
||||
"ctx": 1000000
|
||||
},
|
||||
{
|
||||
"id": "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,
|
||||
"tb21": null,
|
||||
"tb40": 34.8,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": 37.5,
|
||||
"auto": 58.6,
|
||||
"gpqa": null,
|
||||
"critpt": 26.6,
|
||||
"hle": 49.4,
|
||||
"lcr": 86.3,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": 59.2,
|
||||
"gdppdf": 19.2,
|
||||
"ctx": 1048576
|
||||
},
|
||||
{
|
||||
"id": "kimi-k2.7-code",
|
||||
"n": "Kimi K2.7 Code",
|
||||
"lab": "moonshotai",
|
||||
"free": false,
|
||||
"pi": 0.95,
|
||||
"po": 4,
|
||||
"ii": 25.8,
|
||||
"fc": null,
|
||||
"scicode": 47.8,
|
||||
"tb21": 67.4,
|
||||
"tb40": 1,
|
||||
"tbh": 44.7,
|
||||
"tau2": 90.1,
|
||||
"taub": 20.2,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": 24.5,
|
||||
"gpqa": 89.6,
|
||||
"critpt": 10,
|
||||
"hle": 35,
|
||||
"lcr": 79.3,
|
||||
"ifbench": 63.1,
|
||||
"mmmu": null,
|
||||
"gdpv": 26.9,
|
||||
"gdppdf": 11.2,
|
||||
"ctx": 262144
|
||||
},
|
||||
{
|
||||
"id": "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": "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": "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": "mimo-v2.6-flash",
|
||||
"n": "MiMo-V2.6-Flash",
|
||||
"lab": "xiaomi",
|
||||
"free": false,
|
||||
"pi": 0.14,
|
||||
"po": 0.28,
|
||||
"ii": 37.9,
|
||||
"fc": 42.1,
|
||||
"scicode": 51.3,
|
||||
"tb21": null,
|
||||
"tb40": 22.7,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": 64.1,
|
||||
"gpqa": null,
|
||||
"critpt": 12,
|
||||
"hle": 35.1,
|
||||
"lcr": 74.3,
|
||||
"ifbench": null,
|
||||
"mmmu": 73.1,
|
||||
"gdpv": 55.4,
|
||||
"gdppdf": 9,
|
||||
"ctx": 1048576
|
||||
},
|
||||
{
|
||||
"id": "step-5-preview-free",
|
||||
"n": "Step 5 Preview Free",
|
||||
"lab": "stepfun",
|
||||
"free": true,
|
||||
"pi": 0,
|
||||
"po": 0,
|
||||
"ii": null,
|
||||
"fc": null,
|
||||
"scicode": null,
|
||||
"tb21": null,
|
||||
"tb40": null,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": null,
|
||||
"gpqa": null,
|
||||
"critpt": null,
|
||||
"hle": null,
|
||||
"lcr": null,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": null,
|
||||
"gdppdf": null,
|
||||
"ctx": 1000000
|
||||
},
|
||||
{
|
||||
"id": "hy4-preview",
|
||||
"n": "Hy4 preview",
|
||||
"lab": "tencent",
|
||||
"free": false,
|
||||
"pi": 0.834,
|
||||
"po": 2.501,
|
||||
"ii": null,
|
||||
"fc": null,
|
||||
"scicode": null,
|
||||
"tb21": null,
|
||||
"tb40": null,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": null,
|
||||
"gpqa": null,
|
||||
"critpt": null,
|
||||
"hle": null,
|
||||
"lcr": null,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": null,
|
||||
"gdppdf": null,
|
||||
"ctx": 1024000
|
||||
},
|
||||
{
|
||||
"id": "beam-free",
|
||||
"n": "Beam Free",
|
||||
"lab": "reflection",
|
||||
"free": true,
|
||||
"pi": 0,
|
||||
"po": 0,
|
||||
"ii": 30.3,
|
||||
"fc": null,
|
||||
"scicode": 48.5,
|
||||
"tb21": null,
|
||||
"tb40": 3,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": 48.5,
|
||||
"gpqa": null,
|
||||
"critpt": 13.1,
|
||||
"hle": 34.7,
|
||||
"lcr": 78,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": 33.9,
|
||||
"gdppdf": 11.6,
|
||||
"ctx": 1048576
|
||||
},
|
||||
{
|
||||
"id": "cat-jam-free",
|
||||
"n": "Cat Jam Free",
|
||||
"lab": "",
|
||||
"free": true,
|
||||
"pi": 0,
|
||||
"po": 0,
|
||||
"ii": null,
|
||||
"fc": null,
|
||||
"scicode": null,
|
||||
"tb21": null,
|
||||
"tb40": null,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": null,
|
||||
"gpqa": null,
|
||||
"critpt": null,
|
||||
"hle": null,
|
||||
"lcr": null,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": null,
|
||||
"gdppdf": null,
|
||||
"ctx": 1048576
|
||||
},
|
||||
{
|
||||
"id": "claude-haiku-5-5",
|
||||
"n": "Claude Haiku 5.5",
|
||||
"lab": "anthropic",
|
||||
"free": false,
|
||||
"pi": 0.1,
|
||||
"po": 0.5,
|
||||
"ii": 43.4,
|
||||
"fc": 41.8,
|
||||
"scicode": 55,
|
||||
"tb21": null,
|
||||
"tb40": 32.8,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": 53.8,
|
||||
"auto": 35.4,
|
||||
"gpqa": null,
|
||||
"critpt": 18.9,
|
||||
"hle": 44.4,
|
||||
"lcr": 82.7,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": 55.9,
|
||||
"gdppdf": 20.8,
|
||||
"ctx": 1000000
|
||||
},
|
||||
{
|
||||
"id": "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": "muse-spark-1.2-contributor",
|
||||
"n": "Muse Spark 1.2 Contributor",
|
||||
"lab": "meta",
|
||||
"free": false,
|
||||
"pi": 0.1,
|
||||
"po": 0.2,
|
||||
"ii": 39.6,
|
||||
"fc": null,
|
||||
"scicode": 57.4,
|
||||
"tb21": 80.1,
|
||||
"tb40": 7.1,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": 34.8,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": 40.6,
|
||||
"gpqa": 90.4,
|
||||
"critpt": 17.7,
|
||||
"hle": 45.5,
|
||||
"lcr": 79,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": 48.6,
|
||||
"gdppdf": 17.4,
|
||||
"ctx": 1048576
|
||||
},
|
||||
{
|
||||
"id": "glm-5.3-flash",
|
||||
"n": "GLM-5.3-Flash",
|
||||
"lab": "zhipuai",
|
||||
"free": false,
|
||||
"pi": 0.15,
|
||||
"po": 0.5,
|
||||
"ii": 41.8,
|
||||
"fc": 41,
|
||||
"scicode": 51.6,
|
||||
"tb21": 84.3,
|
||||
"tb40": 32.8,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": 47.2,
|
||||
"apex": null,
|
||||
"analyst": 25,
|
||||
"auto": 60.4,
|
||||
"gpqa": 91.2,
|
||||
"critpt": 15.4,
|
||||
"hle": 39.9,
|
||||
"lcr": 80,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": 57.1,
|
||||
"gdppdf": 15.4,
|
||||
"ctx": 1000000
|
||||
},
|
||||
{
|
||||
"id": "qwen3.8-max",
|
||||
"n": "Qwen3.8 Max",
|
||||
"lab": "alibaba",
|
||||
"free": false,
|
||||
"pi": 2,
|
||||
"po": 6,
|
||||
"ii": 45.4,
|
||||
"fc": 43.2,
|
||||
"scicode": 52.1,
|
||||
"tb21": 88.8,
|
||||
"tb40": 38.9,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": 47.8,
|
||||
"apex": 42.4,
|
||||
"analyst": 45,
|
||||
"auto": 56.2,
|
||||
"gpqa": 92.8,
|
||||
"critpt": 17.7,
|
||||
"hle": 43.1,
|
||||
"lcr": 80.3,
|
||||
"ifbench": null,
|
||||
"mmmu": 82.8,
|
||||
"gdpv": 58.2,
|
||||
"gdppdf": 22.8,
|
||||
"ctx": 1000000
|
||||
},
|
||||
{
|
||||
"id": "hy3",
|
||||
"n": "Hy3",
|
||||
"lab": "tencent",
|
||||
"free": false,
|
||||
"pi": 0.14,
|
||||
"po": 0.58,
|
||||
"ii": 25.3,
|
||||
"fc": null,
|
||||
"scicode": 48.6,
|
||||
"tb21": 64.4,
|
||||
"tb40": 0.5,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": 22.9,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": 18.4,
|
||||
"gpqa": 89.7,
|
||||
"critpt": 4.9,
|
||||
"hle": 33.5,
|
||||
"lcr": 79,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": 28.3,
|
||||
"gdppdf": 11.2,
|
||||
"ctx": 256000
|
||||
},
|
||||
{
|
||||
"id": "mimo-v2.5",
|
||||
"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": 24.9,
|
||||
"gdppdf": 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": "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": "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": "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": 46.6,
|
||||
"gdppdf": 22.8,
|
||||
"ctx": 1050000
|
||||
},
|
||||
{
|
||||
"id": "space-bunny",
|
||||
"n": "Space Bunny",
|
||||
"lab": "",
|
||||
"free": false,
|
||||
"pi": 0.15,
|
||||
"po": 0.6,
|
||||
"ii": null,
|
||||
"fc": null,
|
||||
"scicode": null,
|
||||
"tb21": null,
|
||||
"tb40": null,
|
||||
"tbh": null,
|
||||
"tau2": null,
|
||||
"taub": null,
|
||||
"apex": null,
|
||||
"analyst": null,
|
||||
"auto": null,
|
||||
"gpqa": null,
|
||||
"critpt": null,
|
||||
"hle": null,
|
||||
"lcr": null,
|
||||
"ifbench": null,
|
||||
"mmmu": null,
|
||||
"gdpv": null,
|
||||
"gdppdf": null,
|
||||
"ctx": 1048576
|
||||
}
|
||||
];
|
||||
|
||||
@@ -0,0 +1,181 @@
|
||||
{
|
||||
"generated": "2026-10-21T17:03:04.948Z",
|
||||
"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",
|
||||
"hy3",
|
||||
"mimo-v2.5",
|
||||
"deepseek-v4-pro",
|
||||
"glm-5.3",
|
||||
"gpt-5.6-luna",
|
||||
"gpt-6-luna",
|
||||
"space-bunny"
|
||||
],
|
||||
"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": "muse-spark-1.2-contributor",
|
||||
"ii": 39.6
|
||||
},
|
||||
{
|
||||
"id": "glm-5.3-flash",
|
||||
"ii": 41.8
|
||||
},
|
||||
{
|
||||
"id": "qwen3.8-max",
|
||||
"ii": 45.4
|
||||
},
|
||||
{
|
||||
"id": "hy3",
|
||||
"ii": 25.3
|
||||
},
|
||||
{
|
||||
"id": "mimo-v2.5",
|
||||
"ii": 21.8
|
||||
},
|
||||
{
|
||||
"id": "deepseek-v4-pro",
|
||||
"ii": 36
|
||||
},
|
||||
{
|
||||
"id": "glm-5.3",
|
||||
"ii": 44.8
|
||||
},
|
||||
{
|
||||
"id": "gpt-5.6-luna",
|
||||
"ii": 37.3
|
||||
},
|
||||
{
|
||||
"id": "gpt-6-luna",
|
||||
"ii": 38.1
|
||||
},
|
||||
{
|
||||
"id": "space-bunny",
|
||||
"ii": null
|
||||
}
|
||||
],
|
||||
"newModels": [],
|
||||
"removedModels": [],
|
||||
"deltas": [],
|
||||
"liveCatalogSize": 37,
|
||||
"notInLiveCatalog": [
|
||||
"step-5-preview-free",
|
||||
"cat-jam-free",
|
||||
"space-bunny"
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user