AA Coding Index leaderboard
- models measured
- 114
- lead over #2
- +3.6
- median
- 49.3
Leader on AA Coding Index · read October 22
# AA Coding Index, read October 22
leaders = {
"Claude Fable 5.1": 81.6, "Claude Opus 5": 78.0, "GPT-5.6 Sol": 77.4,
}
On October 22, 2026, 114 of our catalog's models had a AA Coding Index result, and Anthropic Claude Fable 5.1 led with 81.6, ahead of Anthropic Claude Opus 5 at 78.0.
The coding part of the Artificial Analysis evaluations, combined into one score from 0 to 100. It is another lab's composite, so the Vibe Coding Index does not average it: it is shown beside our index as a second opinion.
Role in the index
A coding board we show beside the Vibe Coding Index, not inside it: the index keeps the six boards it was defined on, so a score does not move every time a board is added. Read the methodology
| # | Model | Result | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.1Anthropic | 81.6 | 84.2 | $50.00 | |
| 2 | Claude Opus 5Anthropic | 78.0 | 83.0 | $25.00 | |
| 3 | GPT-5.6 SolOpenAI | 77.4 | 73.5 | $20.00 | |
| 4 | GPT-6 AstraOpenAI | 76.9 | 85.1 | $50.00 | |
| 5 | Grok 4.6xAI | 76.8 | 65.7 | $6.00 | |
| 6 | GPT-5.6 TerraOpenAI | 76.7 | 63.9 | $12.00 | |
| 7 | Claude Fable 5Anthropic | 76.5 | 79.3 | $50.00 | |
| 8 | Gemini 3.8 FlashGoogle | 76.3 | 61.6 | $3.75 | |
| 9 | Kimi K3Moonshot AI | 76.2 | 62.3 | $15.00 | |
| 10 | Qwen3.8 Max (0902)Qwen | 76.2 | 62.4 | $6.00 | |
| 11 | Muse Spark 1.3Meta | 75.8 | 57.4 | $4.25 | |
| 12 | GPT-5.5OpenAI | 74.9 | 71.3 | $30.00 | |
| 13 | GLM 5.3Z.ai | 74.8 | 70.6 | $4.40 | |
| 14 | Claude Opus 4.8Anthropic | 74.3 | 65.0 | $25.00 | |
| 15 | Claude Opus 4.7Anthropic | 73.6 | 67.5 | $25.00 | |
| 16 | Grok 4.5xAI | 72.4 | 58.6 | $6.00 | |
| 17 | Muse Spark 1.2Meta | 72.2 | 55.7 | $4.25 | |
| 18 | Qwen3.8 2.4T A95BQwen | 71.9 | Not benchmarked | $6.00 | |
| 19 | Claude Sonnet 5Anthropic | 71.5 | 57.7 | $10.00 | |
| 20 | Gemini 3.7 FlashGoogle | 71.5 | 58.0 | $3.75 | |
| 21 | GLM 5.3 FlashZ.ai | 71.5 | 57.7 | $0.50 | |
| 22 | GPT-5.6 LunaOpenAI | 71.4 | 58.0 | $1.20 | |
| 23 | Muse Spark 1.1Meta | 71.3 | 70.3 | $4.25 | |
| 24 | GPT-5.4OpenAI | 71.1 | 64.4 | $15.00 | |
| 25 | Gemini 3.6 FlashGoogle | 69.2 | 62.5 | $3.75 | |
| 26 | DeepSeek V4 Flash 0731DeepSeek | 69.1 | 51.8 | $0.396 | |
| 27 | DeepSeek V4 Pro 0813DeepSeek | 68.8 | 56.1 | $1.98 | |
| 28 | Gemini 3.1 Pro PreviewGoogle | 68.8 | 32.3 | $12.00 | |
| 29 | GLM 5.2Z.ai | 68.8 | 61.1 | $4.40 | |
| 30 | Qwen3.8 27BQwen | 68.1 | 74.2 | $2.55 | |
| 31 | Qwen3.7 MaxQwen | 66.0 | 54.1 | $4.425 | |
| 32 | DeepSeek V4 Flash Vision ExpDeepSeek | 65.0 | Not benchmarked | $1.32 | |
| 33 | Claude Sonnet 4.6Anthropic | 63.0 | 57.3 | $15.00 | |
| 34 | Kimi K2.6Moonshot AI | 61.8 | 52.1 | $4.00 | |
| 35 | Kimi K2.7 CodeMoonshot AI | 60.8 | 53.4 | $4.00 | |
| 36 | MiMo-V2.5-ProXiaomi | 60.2 | 31.6 | $0.9152 | |
| 37 | DeepSeek V4 Pro 0423DeepSeek | 59.4 | 38.7 | $2.976 | |
| 38 | Hy3 previewTencent | 58.8 | Not benchmarked | $0.60 | |
| 39 | MiniMax M3MiniMax | 58.6 | 39.2 | $1.20 | |
| 40 | Ling 3.0 Flash VLinclusionAI | 57.0 | Not benchmarked | $0.18 | |
| 41 | MiMo-V2.5Xiaomi | 56.8 | 50.0 | $0.336 | |
| 42 | GPT-5.4 MiniOpenAI | 56.1 | 35.8 | $4.50 | |
| 43 | GPT-5.4 NanoOpenAI | 56.1 | 44.8 | $1.25 | |
| 44 | Qwen3.7 PlusQwen | 55.9 | 33.2 | $1.28 | |
| 45 | GLM 5.1Z.ai | 55.8 | 49.2 | $4.40 | |
| 46 | Qwen3.6 PlusQwen | 54.5 | 44.1 | $1.95 | |
| 47 | Qwen3.6 27BQwen | 53.7 | 36.8 | $2.70 | |
| 48 | T Inkling SmallThinking Machines | 52.9 | 27.3 | $1.20 | |
| 49 | Solar Pro 4Upstage | 52.7 | Not benchmarked | $0.60 | |
| 50 | MiniMax M2.7MiniMax | 52.6 | 36.2 | $1.20 | |
| 51 | Claude Sonnet 4.5Anthropic | 52.1 | 39.5 | $15.00 | |
| 52 | T InklingThinking Machines | 52.1 | 31.5 | $4.05 | |
| 53 | DeepSeek V4 Flash 0423DeepSeek | 52.0 | Not benchmarked | $0.28 | |
| 54 | Grok Build 0.1xAI | 51.5 | Not benchmarked | $2.00 | |
| 55 | Ling 3.0 FlashinclusionAI | 50.6 | 29.6 | $0.1215 | |
| 56 | GPT-5.1OpenAI | 49.4 | 40.4 | $10.00 | |
| 57 | Gemini 3.5 Flash LiteGoogle | 49.3 | 49.0 | $2.50 | |
| 58 | Nemotron 3 UltraNVIDIA | 49.3 | 30.0 | $2.40 | |
| 59 | Muse Glimmer 30BMeta | 49.0 | Not benchmarked | $1.35 | |
| 60 | Mistral Medium 3.5Mistral AI | 46.9 | 25.5 | $7.50 | |
| 61 | Kimi K2.5Moonshot AI | 46.8 | 38.6 | $2.85 | |
| 62 | GLM 4.6Z.ai | 45.8 | 8.8 | $2.20 | |
| 63 | LongCat 2.0Meituan | 45.3 | Not benchmarked | $1.20 | |
| 64 | GLM 4.7Z.ai | 45.3 | 55.1 | $2.20 | |
| 65 | DeepSeek V3.2DeepSeek | 44.2 | 30.0 | $0.88 | |
| 66 | Claude Haiku 4.5Anthropic | 43.9 | 35.6 | $5.00 | |
| 67 | DeepSeek V3.1 TerminusDeepSeek | 43.5 | Not benchmarked | $1.0142 | |
| 68 | Gemma 4 31BGoogle | 43.4 | 39.0 | $0.40 | |
| 69 | Qwen3.5-122B-A10BQwen | 43.3 | Not benchmarked | $2.08 | |
| 70 | Grok 4.3xAI | 42.2 | 37.4 | $2.50 | |
| 71 | Qwen3.6 35B A3BQwen | 41.9 | Not benchmarked | $1.00 | |
| 72 | o1OpenAI | 39.7 | Not benchmarked | $60.00 | |
| 73 | Step 3.7 FlashStepFun | 39.6 | Not benchmarked | $1.15 | |
| 74 | Gemma 4 26B A4BGoogle | 39.3 | Not benchmarked | $0.60 | |
| 75 | GPT-5OpenAI | 37.8 | 38.8 | $10.00 | |
| 76 | Nemotron 3 SuperNVIDIA | 37.7 | Not benchmarked | $0.45 | |
| 77 | Qwen3 Coder NextQwen | 36.2 | Not benchmarked | $0.80 | |
| 78 | Gemini 3.1 Flash Lite PreviewGoogle | 34.7 | 22.7 | $1.50 | |
| 79 | Gemini 2.5 ProGoogle | 33.3 | 19.1 | $10.00 | |
| 80 | Devstral 2 2512Mistral AI | 31.3 | Not benchmarked | $2.00 | |
| 81 | Mercury 2Inception | 31.1 | Not benchmarked | $0.75 | |
| 82 | gpt-oss-120bOpenAI | 30.4 | Not benchmarked | $0.50 | |
| 83 | Command ACohere | 27.8 | Not benchmarked | $10.00 | |
| 84 | Nemotron 3.5 LightningNVIDIA | 26.8 | 22.6 | $0.147 | |
| 85 | Mistral Small 4Mistral AI | 26.6 | Not benchmarked | $0.60 | |
| 86 | Trinity Large ThinkingArcee AI | 25.8 | Not benchmarked | $0.80 | |
| 87 | GPT-4o (2024-05-13)OpenAI | 24.2 | Not benchmarked | $15.00 | |
| 88 | Qwen3.5-9BQwen | 23.5 | Not benchmarked | $0.15 | |
| 89 | Nova 2 LiteAmazon | 23.0 | Not benchmarked | $2.50 | |
| 90 | Granite 4.2 8BIBM Granite | 22.4 | Not benchmarked | $0.20 | |
| 91 | Qwen3 235B A22B Thinking 2507Qwen | 22.1 | Not benchmarked | $3.50 | |
| 92 | GPT-4 TurboOpenAI | 21.5 | Not benchmarked | $30.00 | |
| 93 | DeepSeek V3 0324DeepSeek | 21.2 | Not benchmarked | $1.07 | |
| 94 | Mistral Medium 3.1Mistral AI | 20.5 | Not benchmarked | $2.00 | |
| 95 | GPT-4.1 MiniOpenAI | 20.2 | Not benchmarked | $1.60 | |
| 96 | Mistral Large 3 2512Mistral AI | 20.1 | Not benchmarked | $1.50 | |
| 97 | Qwen3 Next 80B A3B ThinkingQwen | 17.4 | Not benchmarked | $1.20 | |
| 98 | Llama 4 MaverickMeta Llama | 16.3 | Not benchmarked | $1.00 | |
| 99 | o3 Mini HighOpenAI | 16.3 | Not benchmarked | $4.40 | |
| 100 | Solar Pro 3Upstage | 16.2 | Not benchmarked | $0.60 | |
| 101 | Ministral 3 14B 2512Mistral AI | 14.4 | Not benchmarked | $0.20 | |
| 102 | Nemotron 3 Nano 30B A3BNVIDIA | 14.4 | Not benchmarked | $0.22 | |
| 103 | GPT-4OpenAI | 13.1 | Not benchmarked | $60.00 | |
| 104 | Llama 3.3 70B InstructMeta Llama | 11.9 | Not benchmarked | $0.72 | |
| 105 | GPT-4o-miniOpenAI | 11.4 | Not benchmarked | $0.60 | |
| 106 | GPT-4.1 NanoOpenAI | 11.1 | Not benchmarked | $0.40 | |
| 107 | GPT-3.5 TurboOpenAI | 10.7 | Not benchmarked | $1.50 | |
| 108 | Gemma 3 27BGoogle | 10.1 | Not benchmarked | $0.30 | |
| 109 | Ministral 3 8B 2512Mistral AI | 9.7 | Not benchmarked | $0.15 | |
| 110 | Llama 4 ScoutMeta Llama | 8.2 | Not benchmarked | $0.50 | |
| 111 | Gemma 3 12BGoogle | 5.8 | Not benchmarked | $0.1625 | |
| 112 | Llama 3.1 8B InstructMeta Llama | 5.4 | Not benchmarked | $0.08 | |
| 113 | Ministral 3 3B 2512Mistral AI | 4.8 | Not benchmarked | $0.10 | |
| 114 | Gemma 3 4BGoogle | 2.7 | Not benchmarked | $0.075 |
Only models in our catalog are listed, and each appears once with its best published run. 213 rows were read from the source on October 22, 2026, and rows that match no catalog model are left out.