Get started

Intelligence Index

Artificial Analysis's Intelligence Index: a composite of the publisher's own evaluation runs across reasoning, knowledge and related tasks, on a 0 to 100 scale, as OpenRouter carries it. 58 models ranked, as carried in OpenRouter's catalog.

retrieved sha256 · 0bb53a77713fartificialanalysis.ai ↗

Most capable64.6Claude Fable 5.2Anthropic
Best value439Ling 3.1 Flash29.6 at $0.068 blended per M
Newest ranked53.9Gemini 4 Hydrogenlisted 12 Nov 2026

The top 26 of 58, 64.6 down to 29.6 on the Intelligence Index. 6 of them are on the frontier below, in the accent.

025507510064.6Claude Fable 5.260.0Gemini 4 Carbon59.1Claude Opus 5.556.9GPT-6 Astra54.6GPT-6.1 Sol54.5Claude Sonnet 5.553.9Gemini 4 Hydrogen51.3GPT-6.1 Terra50.4Gemini 4 Argon50.0Claude Fable 5.146.5Kimi K3.1 Pro44.2Claude Opus 544.2GPT-6 Sol43.6Muse Wonder36.6Muse Spark 1.336.5Claude Haiku 5.535.5Grok 4.734.6Hy433.7Qwen3.8 Max (0902)32.3GPT-5.6 Terra31.7ZGLM 5.331.0Grok 4.630.8Gemini 3.8 Flash30.6TInkling 2 Small29.9MiMo-V2.6-Pro29.6Ling 3.1 FlashIntelligence Index, 0 to 100Claude Fable 5.2: 64.6 on the Intelligence Index · AnthropicClaude Fable 5.264.6 on the Intelligence Index · AnthropicGemini 4 Carbon: 60.0 on the Intelligence Index · GoogleGemini 4 Carbon60.0 on the Intelligence Index · GoogleClaude Opus 5.5: 59.1 on the Intelligence Index · AnthropicClaude Opus 5.559.1 on the Intelligence Index · AnthropicGPT-6 Astra: 56.9 on the Intelligence Index · OpenAIGPT-6 Astra56.9 on the Intelligence Index · OpenAIGPT-6.1 Sol: 54.6 on the Intelligence Index · OpenAIGPT-6.1 Sol54.6 on the Intelligence Index · OpenAIClaude Sonnet 5.5: 54.5 on the Intelligence Index · AnthropicClaude Sonnet 5.554.5 on the Intelligence Index · AnthropicGemini 4 Hydrogen: 53.9 on the Intelligence Index · GoogleGemini 4 Hydrogen53.9 on the Intelligence Index · GoogleGPT-6.1 Terra: 51.3 on the Intelligence Index · OpenAIGPT-6.1 Terra51.3 on the Intelligence Index · OpenAIGemini 4 Argon: 50.4 on the Intelligence Index · GoogleGemini 4 Argon50.4 on the Intelligence Index · GoogleClaude Fable 5.1: 50.0 on the Intelligence Index · AnthropicClaude Fable 5.150.0 on the Intelligence Index · AnthropicKimi K3.1 Pro: 46.5 on the Intelligence Index · MoonshotAIKimi K3.1 Pro46.5 on the Intelligence Index · MoonshotAIClaude Opus 5: 44.2 on the Intelligence Index · AnthropicClaude Opus 544.2 on the Intelligence Index · AnthropicGPT-6 Sol: 44.2 on the Intelligence Index · OpenAIGPT-6 Sol44.2 on the Intelligence Index · OpenAIMuse Wonder: 43.6 on the Intelligence Index · MetaMuse Wonder43.6 on the Intelligence Index · MetaMuse Spark 1.3: 36.6 on the Intelligence Index · MetaMuse Spark 1.336.6 on the Intelligence Index · MetaClaude Haiku 5.5: 36.5 on the Intelligence Index · AnthropicClaude Haiku 5.536.5 on the Intelligence Index · AnthropicGrok 4.7: 35.5 on the Intelligence Index · SpaceXAIGrok 4.735.5 on the Intelligence Index · SpaceXAIHy4: 34.6 on the Intelligence Index · TencentHy434.6 on the Intelligence Index · TencentQwen3.8 Max (0902): 33.7 on the Intelligence Index · QwenQwen3.8 Max (0902)33.7 on the Intelligence Index · QwenGPT-5.6 Terra: 32.3 on the Intelligence Index · OpenAIGPT-5.6 Terra32.3 on the Intelligence Index · OpenAIGLM 5.3: 31.7 on the Intelligence Index · Z.aiGLM 5.331.7 on the Intelligence Index · Z.aiGrok 4.6: 31.0 on the Intelligence Index · SpaceXAIGrok 4.631.0 on the Intelligence Index · SpaceXAIGemini 3.8 Flash: 30.8 on the Intelligence Index · GoogleGemini 3.8 Flash30.8 on the Intelligence Index · GoogleInkling 2 Small: 30.6 on the Intelligence Index · Thinking MachinesInkling 2 Small30.6 on the Intelligence Index · Thinking MachinesMiMo-V2.6-Pro: 29.9 on the Intelligence Index · XiaomiMiMo-V2.6-Pro29.9 on the Intelligence Index · XiaomiLing 3.1 Flash: 29.6 on the Intelligence Index · inclusionAILing 3.1 Flash29.6 on the Intelligence Index · inclusionAI

Every column stands on zero on the index's own 0 to 100 scale, so a column half as tall is half the score, and the maker's mark hangs under each; the leaderboard below carries every ranked model. Scores are Artificial Analysiss, as OpenRouter carries them.

6 models sit on the frontier: nothing scores higher for less.

  • the attractive quadrant
  • the frontier
  • a priced model, in its maker's tone
  • on the frontier, named
The attractive quadrant$0.10$1.00$10.000255075100Blended list price per M tokens, log scaleIndexClaude Fable 5.2: 64.6 · $16.00 blended · Anthropic$16.0064.606 Claude Fable 5.264.6 · $16.00 blended · AnthropicGemini 4 Carbon: 60.0 · $4.00 blended · Google$4.0060.005 Gemini 4 Carbon60.0 · $4.00 blended · GoogleClaude Opus 5.5: 59.1 · $8.00 blended · Anthropic$8.0059.1Claude Opus 5.559.1 · $8.00 blended · AnthropicGPT-6 Astra: 56.9 · $20.00 blended · OpenAI$20.0056.9GPT-6 Astra56.9 · $20.00 blended · OpenAIGPT-6.1 Sol: 54.6 · $4.00 blended · OpenAI$4.0054.6GPT-6.1 Sol54.6 · $4.00 blended · OpenAIClaude Sonnet 5.5: 54.5 · $4.00 blended · Anthropic$4.0054.5Claude Sonnet 5.554.5 · $4.00 blended · AnthropicGemini 4 Hydrogen: 53.9 · $3.00 blended · Google$3.0053.904 Gemini 4 Hydrogen53.9 · $3.00 blended · GoogleGPT-6.1 Terra: 51.3 · $2.00 blended · OpenAI$2.0051.303 GPT-6.1 Terra51.3 · $2.00 blended · OpenAIGemini 4 Argon: 50.4 · $4.00 blended · Google$4.0050.4Gemini 4 Argon50.4 · $4.00 blended · GoogleClaude Fable 5.1: 50.0 · $20.00 blended · Anthropic$20.0050.0Claude Fable 5.150.0 · $20.00 blended · AnthropicKimi K3.1 Pro: 46.5 · $2.281 blended · MoonshotAI$2.28146.5Kimi K3.1 Pro46.5 · $2.281 blended · MoonshotAIClaude Opus 5: 44.2 · $10.00 blended · Anthropic$10.0044.2Claude Opus 544.2 · $10.00 blended · AnthropicGPT-6 Sol: 44.2 · $4.00 blended · OpenAI$4.0044.2GPT-6 Sol44.2 · $4.00 blended · OpenAIMuse Wonder: 43.6 · $8.00 blended · Meta$8.0043.6Muse Wonder43.6 · $8.00 blended · MetaMuse Spark 1.3: 36.6 · $2.00 blended · Meta$2.0036.6Muse Spark 1.336.6 · $2.00 blended · MetaClaude Haiku 5.5: 36.5 · $0.20 blended · Anthropic$0.2036.502 Claude Haiku 5.536.5 · $0.20 blended · AnthropicGrok 4.7: 35.5 · $3.00 blended · SpaceXAI$3.0035.5Grok 4.735.5 · $3.00 blended · SpaceXAIHy4: 34.6 · $0.625 blended · Tencent$0.62534.6Hy434.6 · $0.625 blended · TencentQwen3.8 Max (0902): 33.7 · $3.00 blended · Qwen$3.0033.7Qwen3.8 Max (0902)33.7 · $3.00 blended · QwenGPT-5.6 Terra: 32.3 · $4.50 blended · OpenAI$4.5032.3GPT-5.6 Terra32.3 · $4.50 blended · OpenAIGLM 5.3: 31.7 · $0.402 blended · Z.ai$0.40231.7GLM 5.331.7 · $0.402 blended · Z.aiGrok 4.6: 31.0 · $3.00 blended · SpaceXAI$3.0031.0Grok 4.631.0 · $3.00 blended · SpaceXAIGemini 3.8 Flash: 30.8 · $1.65 blended · Google$1.6530.8Gemini 3.8 Flash30.8 · $1.65 blended · GoogleInkling 2 Small: 30.6 · $0.475 blended · Thinking Machines$0.47530.6Inkling 2 Small30.6 · $0.475 blended · Thinking MachinesMiMo-V2.6-Pro: 29.9 · $0.544 blended · Xiaomi$0.54429.9MiMo-V2.6-Pro29.9 · $0.544 blended · XiaomiLing 3.1 Flash: 29.6 · $0.068 blended · inclusionAI$0.06829.601 Ling 3.1 Flash29.6 · $0.068 blended · inclusionAIMiniMax M3.1 Flash: 29.1 · $0.131 blended · MiniMax$0.13129.1MiniMax M3.1 Flash29.1 · $0.131 blended · MiniMaxDeepSeek V4.1 Flash 1017: 28.6 · $0.152 blended · DeepSeek$0.15228.6DeepSeek V4.1 Flash 101728.6 · $0.152 blended · DeepSeekStep 5 Preview: 28.5 · $1.425 blended · StepFun$1.42528.5Step 5 Preview28.5 · $1.425 blended · StepFunSolar Pro 4: 28.2 · $0.262 blended · Upstage$0.26228.2Solar Pro 428.2 · $0.262 blended · UpstageGPT-6 Luna: 27.9 · $0.20 blended · OpenAI$0.2027.9GPT-6 Luna27.9 · $0.20 blended · OpenAIGLM 5.3 Flash: 27.8 · $0.238 blended · Z.ai$0.23827.8GLM 5.3 Flash27.8 · $0.238 blended · Z.aiMiMo-V2.6-Flash: 26.7 · $0.175 blended · Xiaomi$0.17526.7MiMo-V2.6-Flash26.7 · $0.175 blended · XiaomiMistral Large 4: 26.1 · $1.05 blended · Mistral$1.0526.1Mistral Large 426.1 · $1.05 blended · MistralMuse Spark Open: 24.9 · $2.00 blended · Meta$2.0024.9Muse Spark Open24.9 · $2.00 blended · MetaGPT-5.6 Luna: 23.8 · $0.45 blended · OpenAI$0.4523.8GPT-5.6 Luna23.8 · $0.45 blended · OpenAIDeepSeek V4 Pro 0813: 23.1 · $1.193 blended · DeepSeek$1.19323.1DeepSeek V4 Pro 081323.1 · $1.193 blended · DeepSeekDeepSeek V4 Pro 0423: 20.8 · $1.05 blended · DeepSeek$1.0520.8DeepSeek V4 Pro 042320.8 · $1.05 blended · DeepSeekQwen3.8 27B: 20.1 · $0.581 blended · Qwen$0.58120.1Qwen3.8 27B20.1 · $0.581 blended · QwenMiniMax M3: 18.9 · $0.525 blended · MiniMax$0.52518.9MiniMax M318.9 · $0.525 blended · MiniMaxBeam 1.0 501B A23B: 17.7 · $0.475 blended · Reflection$0.47517.7Beam 1.0 501B A23B17.7 · $0.475 blended · ReflectionKimi K3: 17.4 · $4.144 blended · MoonshotAI$4.14417.4Kimi K317.4 · $4.144 blended · MoonshotAINemotron 3.5 Super VL: 13.6 · $0.238 blended · NVIDIA$0.23813.6Nemotron 3.5 Super VL13.6 · $0.238 blended · NVIDIAInkling Small: 12.9 · $0.638 blended · Thinking Machines$0.63812.9Inkling Small12.9 · $0.638 blended · Thinking MachinesInkling: 12.5 · $1.763 blended · Thinking Machines$1.76312.5Inkling12.5 · $1.763 blended · Thinking MachinesNemotron 3 Ultra: 11.8 · $0.925 blended · NVIDIA$0.92511.8Nemotron 3 Ultra11.8 · $0.925 blended · NVIDIAGemini 3.5 Flash Lite: 11.7 · $0.85 blended · Google$0.8511.7Gemini 3.5 Flash Lite11.7 · $0.85 blended · GoogleClaude Haiku 4.5: 7.4 · $2.00 blended · Anthropic$2.007.4Claude Haiku 4.57.4 · $2.00 blended · AnthropicMuse Glimmer 30B: 6.3 · $0.638 blended · Meta$0.6386.3Muse Glimmer 30B6.3 · $0.638 blended · MetaCommand A+: 6.2 · $0.60 blended · Cohere$0.606.2Command A+6.2 · $0.60 blended · CohereGemini 3.1 Flash Lite Preview: 6.2 · $0.563 blended · Google$0.5636.2Gemini 3.1 Flash Lite Preview6.2 · $0.563 blended · GoogleNemotron 3.5 Lightning: 5.5 · $0.103 blended · NVIDIA$0.1035.5Nemotron 3.5 Lightning5.5 · $0.103 blended · NVIDIAGranite 4.2 8B: 5.1 · $0.082 blended · IBM Granite$0.0825.1Granite 4.2 8B5.1 · $0.082 blended · IBM GraniteMistral Medium 3.5: 4.6 · $3.00 blended · Mistral$3.004.6Mistral Medium 3.54.6 · $3.00 blended · MistralGemma 4 31B: 4.4 · $0.25 blended · Google$0.254.4Gemma 4 31B4.4 · $0.25 blended · GoogleMistral Small 4: 4.3 · $0.262 blended · Mistral$0.2624.3Mistral Small 44.3 · $0.262 blended · Mistralgpt-oss-120b: 3.8 · $0.262 blended · OpenAI$0.2623.8gpt-oss-120b3.8 · $0.262 blended · OpenAI
  1. 01Ling 3.1 Flash29.6 · $0.068 blended
  2. 02Claude Haiku 5.536.5 · $0.20 blended · +6.9 at 3.0x
  3. 03GPT-6.1 Terra51.3 · $2.00 blended · +14.8 at 10x
  4. 04Gemini 4 Hydrogen53.9 · $3.00 blended · +2.6 at 1.5x
  5. 05Gemini 4 Carbon60.0 · $4.00 blended · +6.1 at 1.3x
  6. 06Claude Fable 5.264.6 · $16.00 blended · +4.6 at 4.0x

57 of 58 ranked models carry a list price; 1 is free or unlisted and not in the field. Price is the blended OpenRouter rate, three input tokens to one output, on a logarithmic axis. Each dot is filled in its maker's tone, as the columns above are. The numbered and named dots are the frontier, cheapest first; each step after the first names what it adds over the step before, and at what multiple of the blended price. A hover over any dot names it and its two figures, a click opens the model, and a model named in the picker above keeps its label on. 8 of 57 priced models sit in the attractive quadrant: at or above the median score of 28.5 and at or below the median blended price of $1.05. The tinted corner is that quadrant.

All 58, best first.

Artificial Analysis · 0 to 100
PositionModelAuthorScoreIn / out per MContextListed
01Claude Fable 5.2Anthropic64.6$8.00 / $40.001M
02Gemini 4 CarbonGoogle60.0$2.00 / $10.001.05M
03Claude Opus 5.5Anthropic59.1$4.00 / $20.001M
04GPT-6 AstraOpenAI56.9$10.00 / $50.001.05M
05GPT-6.1 SolOpenAI54.6$2.00 / $10.001.05M
06Claude Sonnet 5.5Anthropic54.5$2.00 / $10.001M
07Gemini 4 HydrogenGoogle53.9$1.50 / $7.501.05M
08GPT-6.1 TerraOpenAI51.3$1.00 / $5.001.05M
09Gemini 4 ArgonGoogle50.4$2.00 / $10.001.05M
10Claude Fable 5.1Anthropic50.0$10.00 / $50.001M
11Kimi K3.1 ProMoonshotAI46.5$0.24 / $8.401.05M
12Claude Opus 5Anthropic44.2$5.00 / $25.001M
13GPT-6 SolOpenAI44.2$2.00 / $10.001.05M
14Muse WonderMeta43.6$4.00 / $20.001.05M
15Muse Spark 1.3Meta36.6$1.25 / $4.251.05M
16Claude Haiku 5.5Anthropic36.5$0.10 / $0.501M
17Grok 4.7SpaceXAI35.5$2.00 / $6.00500k
18Hy4Tencent34.6$0.417 / $1.251.05M
19Qwen3.8 Max (0902)Qwen33.7$2.00 / $6.001M
20GPT-5.6 TerraOpenAI32.3$2.00 / $12.001.05M
21GLM 5.3Z.ai31.7$0.0699 / $1.401.05M
22Grok 4.6SpaceXAI31.0$2.00 / $6.00500k
23Gemini 3.8 FlashGoogle30.8$0.825 / $4.131.05M
24Inkling 2 SmallThinking Machines30.6$0.30 / $1.001.05M
25MiMo-V2.6-ProXiaomi29.9$0.435 / $0.871.05M
26Ling 3.1 FlashinclusionAI29.6$0.045 / $0.1351M
27MiniMax M3.1 FlashMiniMax29.1$0.075 / $0.301.05M
28DeepSeek V4.1 Flash 1017DeepSeek28.6$0.036 / $0.501.05M
29Step 5 PreviewStepFun28.5$1.00 / $2.701M
30Solar Pro 4Upstage28.2$0.15 / $0.60524k
31GPT-6 LunaOpenAI27.9$0.10 / $0.501.05M
32GLM 5.3 FlashZ.ai27.8$0.15 / $0.501.05M
33MiMo-V2.6-FlashXiaomi26.7$0.14 / $0.281.05M
34Mistral Large 4Mistral26.1$0.70 / $2.101.05M
35Muse Spark OpenMeta24.9$1.25 / $4.251.05M
36GPT-5.6 LunaOpenAI23.8$0.20 / $1.201.05M
37DeepSeek V4 Pro 0813DeepSeek23.1$0.111 / $4.441.05M
38DeepSeek V4 Pro 0423DeepSeek20.8$0.90 / $1.501.05M
39Qwen3.8 27BQwen20.1$0.15 / $1.881.02M
40MiniMax M3MiniMax18.9$0.30 / $1.201.05M
41Beam 1.0 501B A23BReflection17.7$0.30 / $1.001.05M
42Kimi K3MoonshotAI17.4$0.192 / $16.001.05M
43Nemotron 3.5 Super VLNVIDIA13.6$0.15 / $0.501.05M
44Inkling SmallThinking Machines12.9$0.45 / $1.20524k
45InklingThinking Machines12.5$1.00 / $4.05524k
46Nemotron 3 UltraNVIDIA11.8$0.50 / $2.20262k
47Gemini 3.5 Flash LiteGoogle11.7$0.30 / $2.501.05M
48Claude Haiku 4.5Anthropic7.4$1.00 / $5.00200k
49Muse Glimmer 30BMeta6.3$0.35 / $1.50131k
50Command A+Cohere6.2$0.30 / $1.50192k
51Gemini 3.1 Flash Lite PreviewGoogle6.2$0.25 / $1.501.05M
52Nemotron 3.5 LightningNVIDIA5.5$0.07 / $0.201.05M
53Granite 4.2 8BIBM Granite5.1$0.06 / $0.15131k
54Mistral Medium 3.5Mistral4.6$1.50 / $7.50262k
55Gemma 4 31BGoogle4.4$0.20 / $0.40262k
56Mistral Small 4Mistral4.3$0.15 / $0.60262k
57gpt-oss-120bOpenAI3.8$0.15 / $0.60131k
58North Mini Code (free)Cohere3.4free256k
What the score tells you

A composite the publisher computes from its own evaluation runs. It orders models on the publisher's tasks, not yours; a gap of a point or two is within what a different task mix would move. It says nothing about price, latency, or how a model behaves on your own cases, which is where Vitna's engine measures quality.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Vitna ran none of these evaluations and adjusted none of these figures.