chore: weekly evaluation refresh 2026-10-26

This commit is contained in:
opencode-go-evals
2026-10-26 05:24:20 +00:00
parent 99489ca17b
commit f3259fdc0a
6 changed files with 1508 additions and 1184 deletions
+447 -375
View File
@@ -2,227 +2,35 @@
// Source: models.dev/api.json (provider "opencode-go") + Artificial Analysis.
export const CATALOG = [
{
"id": "hy4-preview",
"n": "Hy4 preview",
"lab": "tencent",
"released": "2026-08-28",
"id": "mimo-v2.5",
"n": "MiMo V2.5",
"lab": "xiaomi",
"released": "2026-04-22",
"price": {
"in": 0.834,
"out": 2.501
"in": 0.14,
"out": 0.28
},
"free": false,
"ctx": 1024000,
"modalities": "text in → text out",
"description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.",
"canonical": "tencent/hy4-preview",
"ctx": 1000000,
"modalities": "text, image, audio, video in → text out",
"description": "MiMo omni model for text, image, video, audio, and agents",
"canonical": "xiaomi/mimo-v2.5",
"openWeights": true
},
{
"id": "claude-haiku-5-5",
"n": "Claude Haiku 5.5",
"lab": "anthropic",
"released": "2026-10-07",
"id": "gpt-6-luna",
"n": "GPT-6 Luna",
"lab": "openai",
"released": "2026-09-22",
"price": {
"in": 0.1,
"out": 0.5
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, pdf in → text out",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"canonical": "anthropic/claude-haiku-5-5",
"openWeights": false
},
{
"id": "step-5-preview-free",
"n": "Step 5 Preview Free",
"lab": "stepfun",
"released": "2026-09-16",
"price": {
"in": 0,
"out": 0
},
"free": true,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window",
"canonical": "stepfun/step-5-preview",
"openWeights": true
},
{
"id": "deepseek-v4.1-flash",
"n": "DeepSeek V4.1 Flash",
"lab": "deepseek",
"released": "2026-09-10",
"price": {
"in": 0.15,
"out": 0.6
},
"free": false,
"ctx": 1000000,
"modalities": "text, image in → text out",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"canonical": "deepseek/deepseek-v4.1-flash",
"openWeights": true
},
{
"id": "longcat-2.5-preview-free",
"n": "LongCat 2.5 Preview Free",
"lab": "meituan",
"released": "2026-09-25",
"price": {
"in": 0,
"out": 0
},
"free": true,
"ctx": 1000000,
"modalities": "text, image in → text out",
"description": "Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window",
"canonical": "meituan/longcat-2.5-preview",
"openWeights": false
},
{
"id": "minimax-m2.7",
"n": "MiniMax-M2.7",
"lab": "minimax",
"released": "2026-03-18",
"price": {
"in": 0.3,
"out": 1.2
},
"free": false,
"ctx": 204800,
"modalities": "text in → text out",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"canonical": "minimax/MiniMax-M2.7",
"openWeights": true
},
{
"id": "mimo-v2.6-pro",
"n": "MiMo-V2.6-Pro",
"lab": "xiaomi",
"released": "2026-09-22",
"price": {
"in": 0.435,
"out": 0.87
},
"free": false,
"ctx": 1048576,
"modalities": "text, image, audio, video in → text out",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"canonical": "xiaomi/mimo-v2.6-pro",
"openWeights": true
},
{
"id": "kimi-k3",
"n": "Kimi K3",
"lab": "moonshotai",
"released": "2026-07-16",
"price": {
"in": 3,
"out": 15
},
"free": false,
"ctx": 1048576,
"modalities": "text, image, video in → text out",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"canonical": "moonshotai/kimi-k3",
"openWeights": true
},
{
"id": "hy3",
"n": "Hy3",
"lab": "tencent",
"released": "2026-07-06",
"price": {
"in": 0.14,
"out": 0.58
},
"free": false,
"ctx": 256000,
"modalities": "text in → text out",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"canonical": "tencent/hy3",
"openWeights": true
},
{
"id": "mimo-v2.5-pro",
"n": "MiMo V2.5 Pro",
"lab": "xiaomi",
"released": "2026-04-22",
"price": {
"in": 0.435,
"out": 0.87
},
"free": false,
"ctx": 1048576,
"modalities": "text in → text out",
"description": "MiMo pro model for strong multimodal reasoning and agent execution",
"canonical": "xiaomi/mimo-v2.5-pro",
"openWeights": true
},
{
"id": "beam-free",
"n": "Beam Free",
"lab": "reflection",
"released": "2026-10-05",
"price": {
"in": 0,
"out": 0
},
"free": true,
"ctx": 1048576,
"modalities": "text in → text out",
"description": "Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows",
"canonical": "reflection/beam-1.0-501b-a23b",
"openWeights": true
},
{
"id": "qwen3.8-flash",
"n": "Qwen3.8 Flash",
"lab": "alibaba",
"released": "2026-08-26",
"price": {
"in": 0.15,
"out": 0.47
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"canonical": "alibaba/qwen3.8-flash",
"openWeights": false
},
{
"id": "qwen3.8-max",
"n": "Qwen3.8 Max",
"lab": "alibaba",
"released": "2026-08-03",
"price": {
"in": 2,
"out": 6
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows",
"canonical": "alibaba/qwen3.8-max",
"openWeights": false
},
{
"id": "gpt-5.6-luna",
"n": "GPT-5.6 Luna",
"lab": "openai",
"released": "2026-07-09",
"price": {
"in": 0.2,
"out": 1.2
},
"free": false,
"ctx": 1050000,
"modalities": "text, image, pdf in → text out",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"canonical": "openai/gpt-5.6-luna",
"description": "OpenAI's most efficient model for focused, high-volume tasks",
"canonical": "openai/gpt-6-luna",
"openWeights": false
},
{
@@ -242,35 +50,51 @@ export const CATALOG = [
"openWeights": true
},
{
"id": "glm-5.2",
"n": "GLM-5.2",
"lab": "zhipuai",
"released": "2026-06-13",
"id": "hy3",
"n": "Hy3",
"lab": "tencent",
"released": "2026-07-06",
"price": {
"in": 1.4,
"out": 4.4
"in": 0.14,
"out": 0.58
},
"free": false,
"ctx": 1000000,
"ctx": 256000,
"modalities": "text in → text out",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"canonical": "zhipuai/glm-5.2",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"canonical": "tencent/hy3",
"openWeights": true
},
{
"id": "deepseek-v4-pro",
"n": "DeepSeek V4 Pro (New)",
"lab": "deepseek",
"released": "2026-04-24",
"id": "cat-jam-free",
"n": "Cat Jam Free",
"lab": "",
"released": "2026-10-12",
"price": {
"in": 0.66,
"out": 1.98
"in": 0,
"out": 0
},
"free": true,
"ctx": 1048576,
"modalities": "text in → text out",
"description": "A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.",
"canonical": null,
"openWeights": false
},
{
"id": "mimo-v2.6-pro",
"n": "MiMo-V2.6-Pro",
"lab": "xiaomi",
"released": "2026-09-22",
"price": {
"in": 0.435,
"out": 0.87
},
"free": false,
"ctx": 1000000,
"modalities": "text in → text out",
"description": "Flagship DeepSeek model for coding, reasoning, and agentic work",
"canonical": "deepseek/deepseek-v4-pro",
"ctx": 1048576,
"modalities": "text, image, audio, video in → text out",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"canonical": "xiaomi/mimo-v2.6-pro",
"openWeights": true
},
{
@@ -289,54 +113,6 @@ export const CATALOG = [
"canonical": "meta/muse-spark-1.3",
"openWeights": false
},
{
"id": "minimax-m3.1-flash-free",
"n": "MiniMax M3.1 Flash Free",
"lab": "minimax",
"released": "2026-10-19",
"price": {
"in": 0,
"out": 0
},
"free": true,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "Frontier multimodal coding model with 1M context window and tunable thinking depth",
"canonical": "minimax/MiniMax-M3.1-Flash",
"openWeights": false
},
{
"id": "grok-4.7",
"n": "Grok 4.7",
"lab": "xai",
"released": "2026-09-21",
"price": {
"in": 2,
"out": 6
},
"free": false,
"ctx": 500000,
"modalities": "text, image, pdf in → text out",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"canonical": "xai/grok-4.7",
"openWeights": false
},
{
"id": "qwen3.7-plus",
"n": "Qwen3.7 Plus",
"lab": "alibaba",
"released": "2026-06-02",
"price": {
"in": 0.4,
"out": 1.6
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"canonical": "alibaba/qwen3.7-plus",
"openWeights": false
},
{
"id": "gemini-4-argon-contributor",
"n": "Gemini 4 Argon Contributor",
@@ -353,6 +129,150 @@ export const CATALOG = [
"canonical": "google/gemini-4-argon",
"openWeights": false
},
{
"id": "step-5-preview-free",
"n": "Step 5 Preview Free",
"lab": "stepfun",
"released": "2026-09-16",
"price": {
"in": 0,
"out": 0
},
"free": true,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window",
"canonical": "stepfun/step-5-preview",
"openWeights": true
},
{
"id": "gpt-5.6-luna",
"n": "GPT-5.6 Luna",
"lab": "openai",
"released": "2026-07-09",
"price": {
"in": 0.2,
"out": 1.2
},
"free": false,
"ctx": 1050000,
"modalities": "text, image, pdf in → text out",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"canonical": "openai/gpt-5.6-luna",
"openWeights": false
},
{
"id": "kimi-k3.1-pro",
"n": "Kimi K3.1 Pro",
"lab": "moonshotai",
"released": "2026-10-23",
"price": {
"in": 2,
"out": 10
},
"free": false,
"ctx": 1048576,
"modalities": "text, image, video in → text out",
"description": "Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work",
"canonical": "moonshotai/kimi-k3.1-pro",
"openWeights": false
},
{
"id": "qwen3.8-flash",
"n": "Qwen3.8 Flash",
"lab": "alibaba",
"released": "2026-08-26",
"price": {
"in": 0.15,
"out": 0.47
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"canonical": "alibaba/qwen3.8-flash",
"openWeights": false
},
{
"id": "step-5-preview",
"n": "Step 5 Preview",
"lab": "stepfun",
"released": "2026-09-16",
"price": {
"in": 1,
"out": 2.7
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window",
"canonical": "stepfun/step-5-preview",
"openWeights": true
},
{
"id": "qwen3.8-max",
"n": "Qwen3.8 Max",
"lab": "alibaba",
"released": "2026-08-03",
"price": {
"in": 2,
"out": 6
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows",
"canonical": "alibaba/qwen3.8-max",
"openWeights": false
},
{
"id": "hy4-preview",
"n": "Hy4 preview",
"lab": "tencent",
"released": "2026-08-28",
"price": {
"in": 0.834,
"out": 2.501
},
"free": false,
"ctx": 1024000,
"modalities": "text in → text out",
"description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.",
"canonical": "tencent/hy4-preview",
"openWeights": true
},
{
"id": "gemini-4-argon",
"n": "Gemini 4 Argon",
"lab": "google",
"released": "2026-10-13",
"price": {
"in": 2,
"out": 10
},
"free": false,
"ctx": 1048576,
"modalities": "text, image, video, audio, pdf in → text out",
"description": "Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents",
"canonical": "google/gemini-4-argon",
"openWeights": false
},
{
"id": "glm-5.2",
"n": "GLM-5.2",
"lab": "zhipuai",
"released": "2026-06-13",
"price": {
"in": 1.4,
"out": 4.4
},
"free": false,
"ctx": 1000000,
"modalities": "text in → text out",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"canonical": "zhipuai/glm-5.2",
"openWeights": true
},
{
"id": "glm-5.3",
"n": "GLM-5.3",
@@ -380,107 +300,43 @@ export const CATALOG = [
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, video, pdf in → text out",
"modalities": "text, image, video in → text out",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"canonical": "zhipuai/glm-5.3-flash",
"openWeights": true
},
{
"id": "space-bunny",
"n": "Space Bunny",
"lab": "",
"released": "2026-09-23",
"id": "qwen3.7-plus",
"n": "Qwen3.7 Plus",
"lab": "alibaba",
"released": "2026-06-02",
"price": {
"in": 0.4,
"out": 1.6
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"canonical": "alibaba/qwen3.7-plus",
"openWeights": false
},
{
"id": "deepseek-v4.1-flash",
"n": "DeepSeek V4.1 Flash",
"lab": "deepseek",
"released": "2026-09-10",
"price": {
"in": 0.15,
"out": 0.6
},
"free": false,
"ctx": 1048576,
"modalities": "text, image, video in → text out",
"description": "Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input",
"canonical": null,
"openWeights": false
},
{
"id": "kimi-k2.7-code",
"n": "Kimi K2.7 Code",
"lab": "moonshotai",
"released": "2026-06-12",
"price": {
"in": 0.95,
"out": 4
},
"free": false,
"ctx": 262144,
"modalities": "text, image, video in → text out",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"canonical": "moonshotai/kimi-k2.7-code",
"openWeights": true
},
{
"id": "cat-jam-free",
"n": "Cat Jam Free",
"lab": "",
"released": "2026-10-12",
"price": {
"in": 0,
"out": 0
},
"free": true,
"ctx": 1048576,
"modalities": "text in → text out",
"description": "A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.",
"canonical": null,
"openWeights": false
},
{
"id": "gpt-6-luna",
"n": "GPT-6 Luna",
"lab": "openai",
"released": "2026-09-22",
"price": {
"in": 0.1,
"out": 0.5
},
"free": false,
"ctx": 1050000,
"modalities": "text, image, pdf in → text out",
"description": "OpenAI's most efficient model for focused, high-volume tasks",
"canonical": "openai/gpt-6-luna",
"openWeights": false
},
{
"id": "mimo-v2.5",
"n": "MiMo V2.5",
"lab": "xiaomi",
"released": "2026-04-22",
"price": {
"in": 0.14,
"out": 0.28
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, audio, video in → text out",
"description": "MiMo omni model for text, image, video, audio, and agents",
"canonical": "xiaomi/mimo-v2.5",
"modalities": "text, image in → text out",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"canonical": "deepseek/deepseek-v4.1-flash",
"openWeights": true
},
{
"id": "muse-spark-1.2-contributor",
"n": "Muse Spark 1.2 Contributor",
"lab": "meta",
"released": "2026-08-05",
"price": {
"in": 0.1,
"out": 0.2
},
"free": false,
"ctx": 1048576,
"modalities": "text, image, video, pdf, audio in → text out",
"description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.",
"canonical": "meta/muse-spark-1.2",
"openWeights": false
},
{
"id": "mimo-v2.6-flash",
"n": "MiMo-V2.6-Flash",
@@ -497,6 +353,22 @@ export const CATALOG = [
"canonical": "xiaomi/mimo-v2.6-flash",
"openWeights": true
},
{
"id": "kimi-k2.7-code",
"n": "Kimi K2.7 Code",
"lab": "moonshotai",
"released": "2026-06-12",
"price": {
"in": 0.95,
"out": 4
},
"free": false,
"ctx": 262144,
"modalities": "text, image, video in → text out",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"canonical": "moonshotai/kimi-k2.7-code",
"openWeights": true
},
{
"id": "longcat-2.0",
"n": "LongCat-2.0",
@@ -514,32 +386,232 @@ export const CATALOG = [
"openWeights": true
},
{
"id": "step-5-preview",
"n": "Step 5 Preview",
"lab": "stepfun",
"released": "2026-09-16",
"id": "minimax-m3.1-flash",
"n": "MiniMax M3.1 Flash",
"lab": "minimax",
"released": "2026-10-19",
"price": {
"in": 1,
"out": 2.7
"in": 0.15,
"out": 0.6
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window",
"canonical": "stepfun/step-5-preview",
"description": "Frontier multimodal coding model with 1M context window and tunable thinking depth",
"canonical": "minimax/MiniMax-M3.1-Flash",
"openWeights": false
},
{
"id": "claude-haiku-5-5",
"n": "Claude Haiku 5.5",
"lab": "anthropic",
"released": "2026-10-07",
"price": {
"in": 0.1,
"out": 0.5
},
"free": false,
"ctx": 1000000,
"modalities": "text, image, pdf in → text out",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"canonical": "anthropic/claude-haiku-5-5",
"openWeights": false
},
{
"id": "longcat-2.5-preview-free",
"n": "LongCat 2.5 Preview Free",
"lab": "meituan",
"released": "2026-09-25",
"price": {
"in": 0,
"out": 0
},
"free": true,
"ctx": 1000000,
"modalities": "text, image in → text out",
"description": "Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window",
"canonical": "meituan/longcat-2.5-preview",
"openWeights": false
},
{
"id": "grok-4.7",
"n": "Grok 4.7",
"lab": "xai",
"released": "2026-09-21",
"price": {
"in": 2,
"out": 6
},
"free": false,
"ctx": 500000,
"modalities": "text, image, pdf in → text out",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"canonical": "xai/grok-4.7",
"openWeights": false
},
{
"id": "mimo-v2.5-pro",
"n": "MiMo V2.5 Pro",
"lab": "xiaomi",
"released": "2026-04-22",
"price": {
"in": 0.435,
"out": 0.87
},
"free": false,
"ctx": 1048576,
"modalities": "text in → text out",
"description": "MiMo pro model for strong multimodal reasoning and agent execution",
"canonical": "xiaomi/mimo-v2.5-pro",
"openWeights": true
},
{
"id": "space-bunny",
"n": "Space Bunny",
"lab": "",
"released": "2026-09-23",
"price": {
"in": 0.15,
"out": 0.6
},
"free": false,
"ctx": 1048576,
"modalities": "text, image, video in → text out",
"description": "Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input",
"canonical": null,
"openWeights": false
},
{
"id": "kimi-k3",
"n": "Kimi K3",
"lab": "moonshotai",
"released": "2026-07-16",
"price": {
"in": 3,
"out": 15
},
"free": false,
"ctx": 1048576,
"modalities": "text, image, video in → text out",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"canonical": "moonshotai/kimi-k3",
"openWeights": true
},
{
"id": "minimax-m3.1-flash-free",
"n": "MiniMax M3.1 Flash Free",
"lab": "minimax",
"released": "2026-10-19",
"price": {
"in": 0,
"out": 0
},
"free": true,
"ctx": 1000000,
"modalities": "text, image, video in → text out",
"description": "Frontier multimodal coding model with 1M context window and tunable thinking depth",
"canonical": "minimax/MiniMax-M3.1-Flash",
"openWeights": false
},
{
"id": "minimax-m2.7",
"n": "MiniMax-M2.7",
"lab": "minimax",
"released": "2026-03-18",
"price": {
"in": 0.3,
"out": 1.2
},
"free": false,
"ctx": 204800,
"modalities": "text in → text out",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"canonical": "minimax/MiniMax-M2.7",
"openWeights": true
},
{
"id": "iceman-contributor-free",
"n": "Iceman Contributor Free",
"lab": "",
"released": "2026-10-24",
"price": {
"in": 0,
"out": 0
},
"free": true,
"ctx": 262144,
"modalities": "text in → text out",
"description": "Stealth model, free for a limited time",
"canonical": null,
"openWeights": false
},
{
"id": "beam-free",
"n": "Beam Free",
"lab": "reflection",
"released": "2026-10-05",
"price": {
"in": 0,
"out": 0
},
"free": true,
"ctx": 1048576,
"modalities": "text in → text out",
"description": "Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows",
"canonical": "reflection/beam-1.0-501b-a23b",
"openWeights": true
},
{
"id": "deepseek-v4-pro",
"n": "DeepSeek V4 Pro (New)",
"lab": "deepseek",
"released": "2026-04-24",
"price": {
"in": 0.66,
"out": 1.98
},
"free": false,
"ctx": 1000000,
"modalities": "text in → text out",
"description": "Flagship DeepSeek model for coding, reasoning, and agentic work",
"canonical": "deepseek/deepseek-v4-pro",
"openWeights": true
},
{
"id": "muse-spark-1.2-contributor",
"n": "Muse Spark 1.2 Contributor",
"lab": "meta",
"released": "2026-08-05",
"price": {
"in": 0.1,
"out": 0.2
},
"free": false,
"ctx": 1048576,
"modalities": "text, image, video, pdf, audio in → text out",
"description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.",
"canonical": "meta/muse-spark-1.2",
"openWeights": false
}
];
export const SNAPSHOT = {
"generated": "2026-10-21T17:14:47.585Z",
"models": 33,
"newModels": [],
"generated": "2026-10-26T05:24:19.608Z",
"models": 37,
"newModels": [
"kimi-k3.1-pro",
"gemini-4-argon",
"minimax-m3.1-flash",
"iceman-contributor-free"
],
"removedModels": [],
"deltas": [],
"notInLiveCatalog": [
"cat-jam-free",
"gemini-4-argon-contributor",
"step-5-preview-free",
"longcat-2.5-preview-free",
"space-bunny",
"cat-jam-free"
"minimax-m3.1-flash-free"
]
};
+782 -670
View File
File diff suppressed because it is too large Load Diff
+36
View File
@@ -1,6 +1,42 @@
// AUTO-GENERATED by scripts/sync-catalog.mjs — do not edit by hand.
// Rolling week-over-week snapshot of the Intelligence Index.
export const HISTORY = [
{
"date": "2026-10-26",
"scores": {
"mimo-v2.5": 21.8,
"gpt-6-luna": 38.1,
"minimax-m3": 29.2,
"hy3": 25.3,
"mimo-v2.6-pro": 46.3,
"muse-spark-1.3-contributor": 48.1,
"gemini-4-argon-contributor": 52.6,
"gpt-5.6-luna": 37.3,
"kimi-k3.1-pro": 55.1,
"qwen3.8-flash": 39.8,
"step-5-preview": 43.7,
"qwen3.8-max": 45.4,
"gemini-4-argon": 52.6,
"glm-5.2": 33.7,
"glm-5.3": 44.8,
"glm-5.3-flash": 41.8,
"qwen3.7-plus": 25.2,
"deepseek-v4.1-flash": 39.5,
"mimo-v2.6-flash": 37.9,
"kimi-k2.7-code": 25.8,
"longcat-2.0": 19.1,
"minimax-m3.1-flash": 42.7,
"claude-haiku-5-5": 43.4,
"grok-4.7": 46.4,
"mimo-v2.5-pro": 26,
"kimi-k3": 43.6,
"minimax-m3.1-flash-free": 42.7,
"minimax-m2.7": 22.8,
"beam-free": 30.3,
"deepseek-v4-pro": 36,
"muse-spark-1.2-contributor": 39.6
}
},
{
"date": "2026-10-21",
"scores": {
+36
View File
@@ -1,4 +1,40 @@
[
{
"date": "2026-10-26",
"scores": {
"mimo-v2.5": 21.8,
"gpt-6-luna": 38.1,
"minimax-m3": 29.2,
"hy3": 25.3,
"mimo-v2.6-pro": 46.3,
"muse-spark-1.3-contributor": 48.1,
"gemini-4-argon-contributor": 52.6,
"gpt-5.6-luna": 37.3,
"kimi-k3.1-pro": 55.1,
"qwen3.8-flash": 39.8,
"step-5-preview": 43.7,
"qwen3.8-max": 45.4,
"gemini-4-argon": 52.6,
"glm-5.2": 33.7,
"glm-5.3": 44.8,
"glm-5.3-flash": 41.8,
"qwen3.7-plus": 25.2,
"deepseek-v4.1-flash": 39.5,
"mimo-v2.6-flash": 37.9,
"kimi-k2.7-code": 25.8,
"longcat-2.0": 19.1,
"minimax-m3.1-flash": 42.7,
"claude-haiku-5-5": 43.4,
"grok-4.7": 46.4,
"mimo-v2.5-pro": 26,
"kimi-k3": 43.6,
"minimax-m3.1-flash-free": 42.7,
"minimax-m2.7": 22.8,
"beam-free": 30.3,
"deepseek-v4-pro": 36,
"muse-spark-1.2-contributor": 39.6
}
},
{
"date": "2026-10-21",
"scores": {
+148 -120
View File
@@ -1,129 +1,113 @@
{
"generated": "2026-10-21T17:14:47.585Z",
"generated": "2026-10-26T05:24:19.608Z",
"models": [
"hy4-preview",
"claude-haiku-5-5",
"step-5-preview-free",
"deepseek-v4.1-flash",
"longcat-2.5-preview-free",
"minimax-m2.7",
"mimo-v2.6-pro",
"kimi-k3",
"hy3",
"mimo-v2.5-pro",
"beam-free",
"qwen3.8-flash",
"qwen3.8-max",
"gpt-5.6-luna",
"mimo-v2.5",
"gpt-6-luna",
"minimax-m3",
"glm-5.2",
"deepseek-v4-pro",
"hy3",
"cat-jam-free",
"mimo-v2.6-pro",
"muse-spark-1.3-contributor",
"minimax-m3.1-flash-free",
"grok-4.7",
"qwen3.7-plus",
"gemini-4-argon-contributor",
"step-5-preview-free",
"gpt-5.6-luna",
"kimi-k3.1-pro",
"qwen3.8-flash",
"step-5-preview",
"qwen3.8-max",
"hy4-preview",
"gemini-4-argon",
"glm-5.2",
"glm-5.3",
"glm-5.3-flash",
"space-bunny",
"kimi-k2.7-code",
"cat-jam-free",
"gpt-6-luna",
"mimo-v2.5",
"muse-spark-1.2-contributor",
"qwen3.7-plus",
"deepseek-v4.1-flash",
"mimo-v2.6-flash",
"kimi-k2.7-code",
"longcat-2.0",
"step-5-preview"
"minimax-m3.1-flash",
"claude-haiku-5-5",
"longcat-2.5-preview-free",
"grok-4.7",
"mimo-v2.5-pro",
"space-bunny",
"kimi-k3",
"minimax-m3.1-flash-free",
"minimax-m2.7",
"iceman-contributor-free",
"beam-free",
"deepseek-v4-pro",
"muse-spark-1.2-contributor"
],
"scores": [
{
"id": "hy4-preview",
"ii": null
"id": "mimo-v2.5",
"ii": 21.8
},
{
"id": "claude-haiku-5-5",
"ii": 43.4
},
{
"id": "step-5-preview-free",
"ii": null
},
{
"id": "deepseek-v4.1-flash",
"ii": 39.5
},
{
"id": "longcat-2.5-preview-free",
"ii": null
},
{
"id": "minimax-m2.7",
"ii": 22.8
},
{
"id": "mimo-v2.6-pro",
"ii": 46.3
},
{
"id": "kimi-k3",
"ii": 43.6
},
{
"id": "hy3",
"ii": 25.3
},
{
"id": "mimo-v2.5-pro",
"ii": 26
},
{
"id": "beam-free",
"ii": 30.3
},
{
"id": "qwen3.8-flash",
"ii": 39.8
},
{
"id": "qwen3.8-max",
"ii": 45.4
},
{
"id": "gpt-5.6-luna",
"ii": 37.3
"id": "gpt-6-luna",
"ii": 38.1
},
{
"id": "minimax-m3",
"ii": 29.2
},
{
"id": "glm-5.2",
"ii": 33.7
"id": "hy3",
"ii": 25.3
},
{
"id": "deepseek-v4-pro",
"ii": 36
"id": "cat-jam-free",
"ii": null
},
{
"id": "mimo-v2.6-pro",
"ii": 46.3
},
{
"id": "muse-spark-1.3-contributor",
"ii": 48.1
},
{
"id": "minimax-m3.1-flash-free",
"ii": 42.7
},
{
"id": "grok-4.7",
"ii": 46.4
},
{
"id": "qwen3.7-plus",
"ii": 25.2
},
{
"id": "gemini-4-argon-contributor",
"ii": 52.6
},
{
"id": "step-5-preview-free",
"ii": null
},
{
"id": "gpt-5.6-luna",
"ii": 37.3
},
{
"id": "kimi-k3.1-pro",
"ii": 55.1
},
{
"id": "qwen3.8-flash",
"ii": 39.8
},
{
"id": "step-5-preview",
"ii": 43.7
},
{
"id": "qwen3.8-max",
"ii": 45.4
},
{
"id": "hy4-preview",
"ii": null
},
{
"id": "gemini-4-argon",
"ii": 52.6
},
{
"id": "glm-5.2",
"ii": 33.7
},
{
"id": "glm-5.3",
"ii": 44.8
@@ -133,49 +117,93 @@
"ii": 41.8
},
{
"id": "space-bunny",
"ii": null
"id": "qwen3.7-plus",
"ii": 25.2
},
{
"id": "kimi-k2.7-code",
"ii": 25.8
},
{
"id": "cat-jam-free",
"ii": null
},
{
"id": "gpt-6-luna",
"ii": 38.1
},
{
"id": "mimo-v2.5",
"ii": 21.8
},
{
"id": "muse-spark-1.2-contributor",
"ii": 39.6
"id": "deepseek-v4.1-flash",
"ii": 39.5
},
{
"id": "mimo-v2.6-flash",
"ii": 37.9
},
{
"id": "kimi-k2.7-code",
"ii": 25.8
},
{
"id": "longcat-2.0",
"ii": 19.1
},
{
"id": "step-5-preview",
"ii": 43.7
"id": "minimax-m3.1-flash",
"ii": 42.7
},
{
"id": "claude-haiku-5-5",
"ii": 43.4
},
{
"id": "longcat-2.5-preview-free",
"ii": null
},
{
"id": "grok-4.7",
"ii": 46.4
},
{
"id": "mimo-v2.5-pro",
"ii": 26
},
{
"id": "space-bunny",
"ii": null
},
{
"id": "kimi-k3",
"ii": 43.6
},
{
"id": "minimax-m3.1-flash-free",
"ii": 42.7
},
{
"id": "minimax-m2.7",
"ii": 22.8
},
{
"id": "iceman-contributor-free",
"ii": null
},
{
"id": "beam-free",
"ii": 30.3
},
{
"id": "deepseek-v4-pro",
"ii": 36
},
{
"id": "muse-spark-1.2-contributor",
"ii": 39.6
}
],
"newModels": [],
"newModels": [
"kimi-k3.1-pro",
"gemini-4-argon",
"minimax-m3.1-flash",
"iceman-contributor-free"
],
"removedModels": [],
"deltas": [],
"liveCatalogSize": 37,
"liveCatalogSize": 38,
"notInLiveCatalog": [
"cat-jam-free",
"gemini-4-argon-contributor",
"step-5-preview-free",
"longcat-2.5-preview-free",
"space-bunny",
"cat-jam-free"
"minimax-m3.1-flash-free"
]
}