Get started

Coding Index

Artificial Analysis's Coding Index: a composite of the publisher's own coding evaluation runs, on a 0 to 100 scale, as OpenRouter carries it. 118 models ranked, as carried in OpenRouter's catalog.

retrieved sha256 · 0bb53a77713fartificialanalysis.ai ↗

Most capable80.7Claude Fable 5.1Anthropic
Best value1606Ling 3.0 Flash50.6 at $0.032 blended per M
Newest ranked63.5Motif 3listed 2 Nov 2026

The top 26 of 118, 80.7 down to 69.2 on the Coding Index. 7 of them are on the frontier below, in the accent. 0 of the 26 columns match the selection below and are drawn white.

025507510080.7Claude Fable 5.178.3GPT-5.6 Sol78.0Claude Opus 576.9GPT-6 Astra76.7GPT-5.6 Terra76.5Claude Fable 576.3Gemini 3.8 Flash76.2Qwen3.8 Max (0902)76.1Gemini 3.7 Flash75.9Grok 4.675.8Muse Spark 1.374.9GPT-5.574.8ZGLM 5.374.3Claude Opus 4.873.6Claude Opus 4.772.4Grok 4.572.2Muse Spark 1.272.0Kimi K371.9Qwen3.8 2.4T A95B71.5Claude Sonnet 571.5ZGLM 5.3 Flash71.4GPT-5.6 Luna71.3Muse Spark 1.171.1GPT-5.470.1Gemini 3.5 Flash69.2Gemini 3.6 FlashCoding Index, 0 to 100Claude Fable 5.1: 80.7 on the Coding Index · AnthropicClaude Fable 5.180.7 on the Coding Index · AnthropicGPT-5.6 Sol: 78.3 on the Coding Index · OpenAIGPT-5.6 Sol78.3 on the Coding Index · OpenAIClaude Opus 5: 78.0 on the Coding Index · AnthropicClaude Opus 578.0 on the Coding Index · AnthropicGPT-6 Astra: 76.9 on the Coding Index · OpenAIGPT-6 Astra76.9 on the Coding Index · OpenAIGPT-5.6 Terra: 76.7 on the Coding Index · OpenAIGPT-5.6 Terra76.7 on the Coding Index · OpenAIClaude Fable 5: 76.5 on the Coding Index · AnthropicClaude Fable 576.5 on the Coding Index · AnthropicGemini 3.8 Flash: 76.3 on the Coding Index · GoogleGemini 3.8 Flash76.3 on the Coding Index · GoogleQwen3.8 Max (0902): 76.2 on the Coding Index · QwenQwen3.8 Max (0902)76.2 on the Coding Index · QwenGemini 3.7 Flash: 76.1 on the Coding Index · GoogleGemini 3.7 Flash76.1 on the Coding Index · GoogleGrok 4.6: 75.9 on the Coding Index · SpaceXAIGrok 4.675.9 on the Coding Index · SpaceXAIMuse Spark 1.3: 75.8 on the Coding Index · MetaMuse Spark 1.375.8 on the Coding Index · MetaGPT-5.5: 74.9 on the Coding Index · OpenAIGPT-5.574.9 on the Coding Index · OpenAIGLM 5.3: 74.8 on the Coding Index · Z.aiGLM 5.374.8 on the Coding Index · Z.aiClaude Opus 4.8: 74.3 on the Coding Index · AnthropicClaude Opus 4.874.3 on the Coding Index · AnthropicClaude Opus 4.7: 73.6 on the Coding Index · AnthropicClaude Opus 4.773.6 on the Coding Index · AnthropicGrok 4.5: 72.4 on the Coding Index · SpaceXAIGrok 4.572.4 on the Coding Index · SpaceXAIMuse Spark 1.2: 72.2 on the Coding Index · MetaMuse Spark 1.272.2 on the Coding Index · MetaKimi K3: 72.0 on the Coding Index · MoonshotAIKimi K372.0 on the Coding Index · MoonshotAIQwen3.8 2.4T A95B: 71.9 on the Coding Index · QwenQwen3.8 2.4T A95B71.9 on the Coding Index · QwenClaude Sonnet 5: 71.5 on the Coding Index · AnthropicClaude Sonnet 571.5 on the Coding Index · AnthropicGLM 5.3 Flash: 71.5 on the Coding Index · Z.aiGLM 5.3 Flash71.5 on the Coding Index · Z.aiGPT-5.6 Luna: 71.4 on the Coding Index · OpenAIGPT-5.6 Luna71.4 on the Coding Index · OpenAIMuse Spark 1.1: 71.3 on the Coding Index · MetaMuse Spark 1.171.3 on the Coding Index · MetaGPT-5.4: 71.1 on the Coding Index · OpenAIGPT-5.471.1 on the Coding Index · OpenAIGemini 3.5 Flash: 70.1 on the Coding Index · GoogleGemini 3.5 Flash70.1 on the Coding Index · GoogleGemini 3.6 Flash: 69.2 on the Coding Index · GoogleGemini 3.6 Flash69.2 on the Coding Index · Google

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.

10 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 5.1: 80.7 · $20.00 blended · Anthropic$20.0080.710 Claude Fable 5.180.7 · $20.00 blended · AnthropicGPT-5.6 Sol: 78.3 · $8.00 blended · OpenAI$8.0078.309 GPT-5.6 Sol78.3 · $8.00 blended · OpenAIClaude Opus 5: 78.0 · $10.00 blended · Anthropic$10.0078.0Claude Opus 578.0 · $10.00 blended · AnthropicGPT-6 Astra: 76.9 · $20.00 blended · OpenAI$20.0076.9GPT-6 Astra76.9 · $20.00 blended · OpenAIGPT-5.6 Terra: 76.7 · $4.50 blended · OpenAI$4.5076.708 GPT-5.6 Terra76.7 · $4.50 blended · OpenAIClaude Fable 5: 76.5 · $20.00 blended · Anthropic$20.0076.5Claude Fable 576.5 · $20.00 blended · AnthropicGemini 3.8 Flash: 76.3 · $1.65 blended · Google$1.6576.307 Gemini 3.8 Flash76.3 · $1.65 blended · GoogleQwen3.8 Max (0902): 76.2 · $3.00 blended · Qwen$3.0076.2Qwen3.8 Max (0902)76.2 · $3.00 blended · QwenGemini 3.7 Flash: 76.1 · $1.50 blended · Google$1.5076.106 Gemini 3.7 Flash76.1 · $1.50 blended · GoogleGrok 4.6: 75.9 · $3.00 blended · SpaceXAI$3.0075.9Grok 4.675.9 · $3.00 blended · SpaceXAIMuse Spark 1.3: 75.8 · $2.00 blended · Meta$2.0075.8Muse Spark 1.375.8 · $2.00 blended · MetaGPT-5.5: 74.9 · $11.25 blended · OpenAI$11.2574.9GPT-5.574.9 · $11.25 blended · OpenAIGLM 5.3: 74.8 · $0.402 blended · Z.ai$0.40274.805 GLM 5.374.8 · $0.402 blended · Z.aiClaude Opus 4.8: 74.3 · $10.00 blended · Anthropic$10.0074.3Claude Opus 4.874.3 · $10.00 blended · AnthropicClaude Opus 4.7: 73.6 · $10.00 blended · Anthropic$10.0073.6Claude Opus 4.773.6 · $10.00 blended · AnthropicGrok 4.5: 72.4 · $3.00 blended · SpaceXAI$3.0072.4Grok 4.572.4 · $3.00 blended · SpaceXAIMuse Spark 1.2: 72.2 · $2.00 blended · Meta$2.0072.2Muse Spark 1.272.2 · $2.00 blended · MetaKimi K3: 72.0 · $4.144 blended · MoonshotAI$4.14472.0Kimi K372.0 · $4.144 blended · MoonshotAIQwen3.8 2.4T A95B: 71.9 · $3.00 blended · Qwen$3.0071.9Qwen3.8 2.4T A95B71.9 · $3.00 blended · QwenClaude Sonnet 5: 71.5 · $4.00 blended · Anthropic$4.0071.5Claude Sonnet 571.5 · $4.00 blended · AnthropicGLM 5.3 Flash: 71.5 · $0.238 blended · Z.ai$0.23871.504 GLM 5.3 Flash71.5 · $0.238 blended · Z.aiGPT-5.6 Luna: 71.4 · $0.45 blended · OpenAI$0.4571.4GPT-5.6 Luna71.4 · $0.45 blended · OpenAIMuse Spark 1.1: 71.3 · $2.00 blended · Meta$2.0071.3Muse Spark 1.171.3 · $2.00 blended · MetaGPT-5.4: 71.1 · $5.625 blended · OpenAI$5.62571.1GPT-5.471.1 · $5.625 blended · OpenAIGemini 3.5 Flash: 70.1 · $3.375 blended · Google$3.37570.1Gemini 3.5 Flash70.1 · $3.375 blended · GoogleGemini 3.6 Flash: 69.2 · $1.50 blended · Google$1.5069.2Gemini 3.6 Flash69.2 · $1.50 blended · GoogleDeepSeek V4 Flash 0731: 69.1 · $0.09 blended · DeepSeek$0.0969.103 DeepSeek V4 Flash 073169.1 · $0.09 blended · DeepSeekDeepSeek V4 Pro 0813: 68.8 · $1.193 blended · DeepSeek$1.19368.8DeepSeek V4 Pro 081368.8 · $1.193 blended · DeepSeekGemini 3.1 Pro Preview: 68.8 · $4.50 blended · Google$4.5068.8Gemini 3.1 Pro Preview68.8 · $4.50 blended · GoogleGLM 5.2: 68.8 · $1.705 blended · Z.ai$1.70568.8GLM 5.268.8 · $1.705 blended · Z.aiQwen3.8 27B: 68.1 · $0.581 blended · Qwen$0.58168.1Qwen3.8 27B68.1 · $0.581 blended · QwenQwen3.7 Max: 66.0 · $2.213 blended · Qwen$2.21366.0Qwen3.7 Max66.0 · $2.213 blended · QwenDeepSeek V4 Flash Vision Exp: 65.0 · $0.66 blended · DeepSeek$0.6665.0DeepSeek V4 Flash Vision Exp65.0 · $0.66 blended · DeepSeekMotif 3: 63.5 · $0.525 blended · Motif Technologies$0.52563.5Motif 363.5 · $0.525 blended · Motif TechnologiesClaude Sonnet 4.6: 63.0 · $6.00 blended · Anthropic$6.0063.0Claude Sonnet 4.663.0 · $6.00 blended · AnthropicKimi K2.6: 61.8 · $1.34 blended · MoonshotAI$1.3461.8Kimi K2.661.8 · $1.34 blended · MoonshotAIKimi K2.7 Code: 60.8 · $1.463 blended · MoonshotAI$1.46360.8Kimi K2.7 Code60.8 · $1.463 blended · MoonshotAIMiMo-V2.5-Pro: 60.2 · $0.544 blended · Xiaomi$0.54460.2MiMo-V2.5-Pro60.2 · $0.544 blended · XiaomiHy3 preview: 58.8 · $0.285 blended · Tencent$0.28558.8Hy3 preview58.8 · $0.285 blended · TencentMiniMax M3: 58.6 · $0.525 blended · MiniMax$0.52558.6MiniMax M358.6 · $0.525 blended · MiniMaxLing 3.0 Flash VL: 57.0 · $0.09 blended · inclusionAI$0.0957.0Ling 3.0 Flash VL57.0 · $0.09 blended · inclusionAIMiMo-V2.5: 56.8 · $0.80 blended · Xiaomi$0.8056.8MiMo-V2.556.8 · $0.80 blended · XiaomiDeepSeek V4 Flash 0423: 56.2 · $0.113 blended · DeepSeek$0.11356.2DeepSeek V4 Flash 042356.2 · $0.113 blended · DeepSeekGPT-5.4 Mini: 56.1 · $1.688 blended · OpenAI$1.68856.1GPT-5.4 Mini56.1 · $1.688 blended · OpenAIGPT-5.4 Nano: 56.1 · $0.463 blended · OpenAI$0.46356.1GPT-5.4 Nano56.1 · $0.463 blended · OpenAIQwen3.7 Plus: 55.9 · $0.56 blended · Qwen$0.5655.9Qwen3.7 Plus55.9 · $0.56 blended · QwenGLM 5.1: 55.8 · $2.15 blended · Z.ai$2.1555.8GLM 5.155.8 · $2.15 blended · Z.aiQwen3.6 Plus: 54.5 · $0.731 blended · Qwen$0.73154.5Qwen3.6 Plus54.5 · $0.731 blended · QwenQwen3.6 27B: 53.7 · $1.04 blended · Qwen$1.0453.7Qwen3.6 27B53.7 · $1.04 blended · QwenInkling Small: 52.9 · $0.638 blended · Thinking Machines$0.63852.9Inkling Small52.9 · $0.638 blended · Thinking MachinesSolar Pro 4: 52.7 · $0.262 blended · Upstage$0.26252.7Solar Pro 452.7 · $0.262 blended · UpstageMiniMax M2.7: 52.6 · $0.368 blended · MiniMax$0.36852.6MiniMax M2.752.6 · $0.368 blended · MiniMaxClaude Sonnet 4.5: 52.1 · $6.00 blended · Anthropic$6.0052.1Claude Sonnet 4.552.1 · $6.00 blended · AnthropicInkling: 52.1 · $1.763 blended · Thinking Machines$1.76352.1Inkling52.1 · $1.763 blended · Thinking MachinesGrok Build 0.1: 51.5 · $1.25 blended · SpaceXAI$1.2551.5Grok Build 0.151.5 · $1.25 blended · SpaceXAILing 3.0 Flash: 50.6 · $0.032 blended · inclusionAI$0.03250.602 Ling 3.0 Flash50.6 · $0.032 blended · inclusionAIGPT-5.1: 49.4 · $3.438 blended · OpenAI$3.43849.4GPT-5.149.4 · $3.438 blended · OpenAIGemini 3.5 Flash Lite: 49.3 · $0.85 blended · Google$0.8549.3Gemini 3.5 Flash Lite49.3 · $0.85 blended · GoogleNemotron 3 Ultra: 49.3 · $0.925 blended · NVIDIA$0.92549.3Nemotron 3 Ultra49.3 · $0.925 blended · NVIDIAMuse Glimmer 30B: 49.0 · $0.638 blended · Meta$0.63849.0Muse Glimmer 30B49.0 · $0.638 blended · MetaQwen3.5 397B A17B: 48.2 · $1.088 blended · Qwen$1.08848.2Qwen3.5 397B A17B48.2 · $1.088 blended · QwenMistral Medium 3.5: 46.9 · $3.00 blended · Mistral$3.0046.9Mistral Medium 3.546.9 · $3.00 blended · MistralKimi K2.5: 46.8 · $1.00 blended · MoonshotAI$1.0046.8Kimi K2.546.8 · $1.00 blended · MoonshotAIGLM 4.6: 45.8 · $0.875 blended · Z.ai$0.87545.8GLM 4.645.8 · $0.875 blended · Z.aiQwen3.5-122B-A10B: 45.7 · $0.715 blended · Qwen$0.71545.7Qwen3.5-122B-A10B45.7 · $0.715 blended · QwenLongCat 2.0: 45.3 · $0.525 blended · Meituan$0.52545.3LongCat 2.045.3 · $0.525 blended · MeituanGLM 4.7: 45.3 · $0.738 blended · Z.ai$0.73845.3GLM 4.745.3 · $0.738 blended · Z.aiDeepSeek V3.2: 44.2 · $0.29 blended · DeepSeek$0.2944.2DeepSeek V3.244.2 · $0.29 blended · DeepSeekClaude Haiku 4.5: 43.9 · $2.00 blended · Anthropic$2.0043.9Claude Haiku 4.543.9 · $2.00 blended · AnthropicDeepSeek V3.1 Terminus: 43.5 · $0.453 blended · DeepSeek$0.45343.5DeepSeek V3.1 Terminus43.5 · $0.453 blended · DeepSeekGemma 4 31B: 43.4 · $0.25 blended · Google$0.2543.4Gemma 4 31B43.4 · $0.25 blended · GoogleGrok 4.3: 42.2 · $1.563 blended · SpaceXAI$1.56342.2Grok 4.342.2 · $1.563 blended · SpaceXAIQwen3.6 35B A3B: 41.9 · $0.30 blended · Qwen$0.3041.9Qwen3.6 35B A3B41.9 · $0.30 blended · QwenStep 3.7 Flash: 39.6 · $0.438 blended · StepFun$0.43839.6Step 3.7 Flash39.6 · $0.438 blended · StepFunGemma 4 26B A4B: 39.3 · $0.143 blended · Google$0.14339.3Gemma 4 26B A4B39.3 · $0.143 blended · GoogleGPT-5: 37.8 · $3.438 blended · OpenAI$3.43837.8GPT-537.8 · $3.438 blended · OpenAINemotron 3 Super: 37.7 · $0.156 blended · NVIDIA$0.15637.7Nemotron 3 Super37.7 · $0.156 blended · NVIDIAQwen3.5-35B-A3B: 37.0 · $0.355 blended · Qwen$0.35537.0Qwen3.5-35B-A3B37.0 · $0.355 blended · QwenQwen3 Coder Next: 36.2 · $0.29 blended · Qwen$0.2936.2Qwen3 Coder Next36.2 · $0.29 blended · QwenGemini 3.1 Flash Lite Preview: 34.7 · $0.563 blended · Google$0.56334.7Gemini 3.1 Flash Lite Preview34.7 · $0.563 blended · GoogleGemini 2.5 Pro: 33.3 · $3.438 blended · Google$3.43833.3Gemini 2.5 Pro33.3 · $3.438 blended · GoogleDevstral 2 2512: 31.3 · $0.80 blended · Mistral$0.8031.3Devstral 2 251231.3 · $0.80 blended · Mistralgpt-oss-120b: 30.4 · $0.262 blended · OpenAI$0.26230.4gpt-oss-120b30.4 · $0.262 blended · OpenAIQwen3.5-9B: 28.7 · $0.19 blended · Qwen$0.1928.7Qwen3.5-9B28.7 · $0.19 blended · QwenCommand A+: 27.8 · $0.60 blended · Cohere$0.6027.8Command A+27.8 · $0.60 blended · CohereNemotron 3.5 Lightning: 26.8 · $0.103 blended · NVIDIA$0.10326.8Nemotron 3.5 Lightning26.8 · $0.103 blended · NVIDIAMistral Small 4: 26.6 · $0.262 blended · Mistral$0.26226.6Mistral Small 426.6 · $0.262 blended · MistralLing 3.0 Tiny: 26.5 · $0.023 blended · inclusionAI$0.02326.501 Ling 3.0 Tiny26.5 · $0.023 blended · inclusionAIGPT-4o (2024-05-13): 24.2 · $7.50 blended · OpenAI$7.5024.2GPT-4o (2024-05-13)24.2 · $7.50 blended · OpenAINova 2 Lite: 23.0 · $0.85 blended · Amazon$0.8523.0Nova 2 Lite23.0 · $0.85 blended · AmazonGranite 4.2 8B: 22.4 · $0.082 blended · IBM Granite$0.08222.4Granite 4.2 8B22.4 · $0.082 blended · IBM GraniteQwen3 235B A22B Thinking 2507: 22.1 · $1.213 blended · Qwen$1.21322.1Qwen3 235B A22B Thinking 250722.1 · $1.213 blended · QwenGPT-4 Turbo (batch): 21.5 · $7.50 blended · OpenAI$7.5021.5GPT-4 Turbo (batch)21.5 · $7.50 blended · OpenAIDeepSeek V3 0324: 21.2 · $0.502 blended · DeepSeek$0.50221.2DeepSeek V3 032421.2 · $0.502 blended · DeepSeekKimi K2 Thinking: 21.0 · $1.075 blended · MoonshotAI$1.07521.0Kimi K2 Thinking21.0 · $1.075 blended · MoonshotAIgpt-oss-20b: 20.7 · $0.036 blended · OpenAI$0.03620.7gpt-oss-20b20.7 · $0.036 blended · OpenAIMistral Medium 3.1: 20.5 · $0.88 blended · Mistral$0.8820.5Mistral Medium 3.120.5 · $0.88 blended · MistralGPT-4.1 Mini: 20.2 · $0.70 blended · OpenAI$0.7020.2GPT-4.1 Mini20.2 · $0.70 blended · OpenAIMistral Large 3 2512: 20.1 · $0.75 blended · Mistral$0.7520.1Mistral Large 3 251220.1 · $0.75 blended · MistralLlama 4 Maverick: 16.3 · $0.513 blended · Meta Llama$0.51316.3Llama 4 Maverick16.3 · $0.513 blended · Meta LlamaGPT-5 Mini: 15.6 · $0.688 blended · OpenAI$0.68815.6GPT-5 Mini15.6 · $0.688 blended · OpenAIQwen3 32B: 15.3 · $0.13 blended · Qwen$0.1315.3Qwen3 32B15.3 · $0.13 blended · QwenMinistral 3 14B 2512: 14.4 · $0.20 blended · Mistral$0.2014.4Ministral 3 14B 251214.4 · $0.20 blended · MistralNemotron 3 Nano 30B A3B: 14.4 · $0.105 blended · NVIDIA$0.10514.4Nemotron 3 Nano 30B A3B14.4 · $0.105 blended · NVIDIAQwen3 14B: 13.8 · $0.15 blended · Qwen$0.1513.8Qwen3 14B13.8 · $0.15 blended · QwenGPT-4: 13.1 · $37.50 blended · OpenAI$37.5013.1GPT-413.1 · $37.50 blended · OpenAILlama 3.3 70B Instruct: 11.9 · $0.71 blended · Meta Llama$0.7111.9Llama 3.3 70B Instruct11.9 · $0.71 blended · Meta LlamaGPT-4o-mini: 11.4 · $0.262 blended · OpenAI$0.26211.4GPT-4o-mini11.4 · $0.262 blended · OpenAIGPT-4.1 Nano: 11.1 · $0.175 blended · OpenAI$0.17511.1GPT-4.1 Nano11.1 · $0.175 blended · OpenAIGemma 3 27B: 10.1 · $0.148 blended · Google$0.14810.1Gemma 3 27B10.1 · $0.148 blended · GoogleMinistral 3 8B 2512: 9.7 · $0.15 blended · Mistral$0.159.7Ministral 3 8B 25129.7 · $0.15 blended · MistralLlama 4 Scout: 8.2 · $0.15 blended · Meta Llama$0.158.2Llama 4 Scout8.2 · $0.15 blended · Meta LlamaGemma 3 12B: 5.8 · $0.075 blended · Google$0.0755.8Gemma 3 12B5.8 · $0.075 blended · GoogleLlama 3.1 8B Instruct: 5.4 · $0.025 blended · Meta Llama$0.0255.4Llama 3.1 8B Instruct5.4 · $0.025 blended · Meta LlamaMinistral 3 3B 2512: 4.8 · $0.10 blended · Mistral$0.104.8Ministral 3 3B 25124.8 · $0.10 blended · MistralGemma 3 4B: 2.7 · $0.063 blended · Google$0.0632.7Gemma 3 4B2.7 · $0.063 blended · Google
  1. 01Ling 3.0 Tiny26.5 · $0.023 blended
  2. 02Ling 3.0 Flash50.6 · $0.032 blended · +24.1 at 1.4x
  3. 03DeepSeek V4 Flash 073169.1 · $0.09 blended · +18.5 at 2.9x
  4. 04GLM 5.3 Flash71.5 · $0.238 blended · +2.4 at 2.6x
  5. 05GLM 5.374.8 · $0.402 blended · +3.3 at 1.7x
  6. 06Gemini 3.7 Flash76.1 · $1.50 blended · +1.3 at 3.7x
  7. 07Gemini 3.8 Flash76.3 · $1.65 blended · +0.2 at 1.1x
  8. 08GPT-5.6 Terra76.7 · $4.50 blended · +0.4 at 2.7x
  9. 09GPT-5.6 Sol78.3 · $8.00 blended · +1.6 at 1.8x
  10. 10Claude Fable 5.180.7 · $20.00 blended · +2.4 at 2.5x

116 of 118 ranked models carry a list price; 2 are 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. 19 of 116 priced models sit in the attractive quadrant: at or above the median score of 49.3 and at or below the median blended price of $0.734. The tinted corner is that quadrant. 8 of the 116 crosses match the selection below and are drawn white.

8 of 118.

Artificial Analysis · 0 to 100
PositionModelAuthorScoreIn / out per MContextListed
62Mistral Medium 3.5Mistral46.9$1.50 / $7.50262k
83Devstral 2 2512Mistral31.3$0.40 / $2.00262k
88Mistral Small 4Mistral26.6$0.15 / $0.60262k
98Mistral Medium 3.1Mistral20.5$0.44 / $2.20131k
100Mistral Large 3 2512Mistral20.1$0.50 / $1.50262k
104Ministral 3 14B 2512Mistral14.4$0.20 / $0.20262k
113Ministral 3 8B 2512Mistral9.7$0.15 / $0.15262k
117Ministral 3 3B 2512Mistral4.8$0.10 / $0.10131k

The field and the frontier above are the whole board and do not narrow with this table: a frontier drawn through 8 of 118 models would say nothing beats them on both while something in the same board does. The models this table holds are drawn white in the figures instead.

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.