AA Agentic Index leaderboard
- models measured
- 87
- lead over #2
- +1.4
- median
- 18.5
Leader on AA Agentic Index · read October 22
On October 22, 2026, 87 of our catalog's models had a AA Agentic Index result, and Anthropic Claude Fable 5.1 led with 57.9, ahead of Anthropic Claude Opus 5 at 56.5.
The agentic part of the Artificial Analysis evaluations: tasks where the model acts over several steps with tools, combined into one score from 0 to 100.
Role in the index
AA Agentic Index carries 20% of the Agentic Index. A model missing it is scored on the other benchmarks of that index. Read the methodology
| # | Model | Result | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.1Anthropic | 57.9 | 84.2 | $50.00 | |
| 2 | Claude Opus 5Anthropic | 56.5 | 83.0 | $25.00 | |
| 3 | Qwen3.8 Max (0902)Qwen | 56.0 | 62.4 | $6.00 | |
| 4 | Muse Spark 1.3Meta | 55.5 | 57.4 | $4.25 | |
| 5 | GLM 5.3Z.ai | 53.1 | 70.6 | $4.40 | |
| 6 | Grok 4.6xAI | 53.0 | 65.7 | $6.00 | |
| 7 | GPT-6 AstraOpenAI | 51.0 | 85.1 | $50.00 | |
| 8 | GLM 5.3 FlashZ.ai | 50.9 | 57.7 | $0.50 | |
| 9 | Claude Fable 5Anthropic | 50.7 | 79.3 | $50.00 | |
| 10 | GPT-5.6 SolOpenAI | 50.2 | 73.5 | $20.00 | |
| 11 | Qwen3.8 2.4T A95BQwen | 50.1 | Not benchmarked | $6.00 | |
| 12 | Kimi K3Moonshot AI | 50.0 | 62.3 | $15.00 | |
| 13 | DeepSeek V4 Flash Vision ExpDeepSeek | 47.5 | Not benchmarked | $1.32 | |
| 14 | Qwen3.8 27BQwen | 45.8 | 74.2 | $2.55 | |
| 15 | Claude Sonnet 5Anthropic | 43.6 | 57.7 | $10.00 | |
| 16 | Muse Spark 1.2Meta | 43.2 | 55.7 | $4.25 | |
| 17 | GPT-5.6 TerraOpenAI | 43.2 | 63.9 | $12.00 | |
| 18 | GPT-5.6 LunaOpenAI | 42.1 | 58.0 | $1.20 | |
| 19 | Claude Opus 4.8Anthropic | 41.9 | 65.0 | $25.00 | |
| 20 | DeepSeek V4 Pro 0813DeepSeek | 41.3 | 56.1 | $1.98 | |
| 21 | Grok 4.5xAI | 41.2 | 58.6 | $6.00 | |
| 22 | DeepSeek V4 Flash 0731DeepSeek | 41.0 | 51.8 | $0.396 | |
| 23 | Gemini 3.8 FlashGoogle | 40.2 | 61.6 | $3.75 | |
| 24 | Claude Opus 4.7Anthropic | 38.6 | 67.5 | $25.00 | |
| 25 | GLM 5.2Z.ai | 38.4 | 61.1 | $4.40 | |
| 26 | GPT-5.5OpenAI | 36.4 | 71.3 | $30.00 | |
| 27 | Claude Sonnet 4.6Anthropic | 31.8 | 57.3 | $15.00 | |
| 28 | MiniMax M3MiniMax | 29.5 | 39.2 | $1.20 | |
| 29 | Gemini 3.6 FlashGoogle | 29.0 | 62.5 | $3.75 | |
| 30 | Ling 3.0 Flash VLinclusionAI | 28.7 | Not benchmarked | $0.18 | |
| 31 | DeepSeek V4 Flash 0423DeepSeek | 26.3 | Not benchmarked | $0.28 | |
| 32 | DeepSeek V4 Pro 0423DeepSeek | 26.3 | 38.7 | $2.976 | |
| 33 | Muse Spark 1.1Meta | 25.8 | 70.3 | $4.25 | |
| 34 | Hy3 previewTencent | 24.1 | Not benchmarked | $0.60 | |
| 35 | GLM 5.1Z.ai | 23.9 | 49.2 | $4.40 | |
| 36 | T Inkling SmallThinking Machines | 23.5 | 27.3 | $1.20 | |
| 37 | Qwen3.7 MaxQwen | 22.5 | 54.1 | $4.425 | |
| 38 | T InklingThinking Machines | 22.5 | 31.5 | $4.05 | |
| 39 | MiMo-V2.5-ProXiaomi | 21.3 | 31.6 | $0.9152 | |
| 40 | Kimi K2.7 CodeMoonshot AI | 21.0 | 53.4 | $4.00 | |
| 41 | Kimi K2.6Moonshot AI | 20.5 | 52.1 | $4.00 | |
| 42 | Nemotron 3 UltraNVIDIA | 20.1 | 30.0 | $2.40 | |
| 43 | Ling 3.0 FlashinclusionAI | 19.3 | 29.6 | $0.1215 | |
| 44 | Qwen3.6 27BQwen | 18.5 | 36.8 | $2.70 | |
| 45 | GPT-5.4 MiniOpenAI | 17.9 | 35.8 | $4.50 | |
| 46 | Qwen3.7 PlusQwen | 17.5 | 33.2 | $1.28 | |
| 47 | GPT-5.4 NanoOpenAI | 16.0 | 44.8 | $1.25 | |
| 48 | Claude Sonnet 4.5Anthropic | 15.8 | 39.5 | $15.00 | |
| 49 | MiMo-V2.5Xiaomi | 15.8 | 50.0 | $0.336 | |
| 50 | Grok 4.3xAI | 15.5 | 37.4 | $2.50 | |
| 51 | MiniMax M2.7MiniMax | 15.3 | 36.2 | $1.20 | |
| 52 | Gemini 3.5 Flash LiteGoogle | 14.3 | 49.0 | $2.50 | |
| 53 | LongCat 2.0Meituan | 14.0 | Not benchmarked | $1.20 | |
| 54 | Qwen3.6 35B A3BQwen | 13.1 | Not benchmarked | $1.00 | |
| 55 | Muse Glimmer 30BMeta | 8.5 | Not benchmarked | $1.35 | |
| 56 | Gemini 3.1 Pro PreviewGoogle | 8.2 | 32.3 | $12.00 | |
| 57 | Claude Haiku 4.5Anthropic | 8.0 | 35.6 | $5.00 | |
| 58 | Mistral Medium 3.5Mistral AI | 7.0 | 25.5 | $7.50 | |
| 59 | DeepSeek V3.1 TerminusDeepSeek | 6.8 | Not benchmarked | $1.0142 | |
| 60 | Gemma 4 31BGoogle | 4.2 | 39.0 | $0.40 | |
| 61 | gpt-oss-120bOpenAI | 3.7 | Not benchmarked | $0.50 | |
| 62 | Nemotron 3.5 LightningNVIDIA | 3.5 | 22.6 | $0.147 | |
| 63 | Gemma 4 26B A4BGoogle | 2.9 | Not benchmarked | $0.60 | |
| 64 | Devstral 2 2512Mistral AI | 2.3 | Not benchmarked | $2.00 | |
| 65 | Mistral Medium 3.1Mistral AI | 1.9 | Not benchmarked | $2.00 | |
| 66 | Nemotron 3 SuperNVIDIA | 1.7 | Not benchmarked | $0.45 | |
| 67 | Gemini 2.5 ProGoogle | 1.6 | 19.1 | $10.00 | |
| 68 | Gemini 3.1 Flash Lite PreviewGoogle | 1.6 | 22.7 | $1.50 | |
| 69 | Mercury 2Inception | 1.6 | Not benchmarked | $0.75 | |
| 70 | Solar Pro 3Upstage | 1.4 | Not benchmarked | $0.60 | |
| 71 | Granite 4.2 8BIBM Granite | 1.3 | Not benchmarked | $0.20 | |
| 72 | Qwen3 235B A22B Thinking 2507Qwen | 1.3 | Not benchmarked | $3.50 | |
| 73 | Ministral 3 14B 2512Mistral AI | 1.1 | Not benchmarked | $0.20 | |
| 74 | Trinity Large ThinkingArcee AI | 1.0 | Not benchmarked | $0.80 | |
| 75 | Command ACohere | 1.0 | Not benchmarked | $10.00 | |
| 76 | Mistral Large 3 2512Mistral AI | 1.0 | Not benchmarked | $1.50 | |
| 77 | Nemotron 3 Nano 30B A3BNVIDIA | 1.0 | Not benchmarked | $0.22 | |
| 78 | o3 Mini HighOpenAI | 0.9 | Not benchmarked | $4.40 | |
| 79 | Qwen3 Coder NextQwen | 0.9 | Not benchmarked | $0.80 | |
| 80 | DeepSeek V3 0324DeepSeek | 0.8 | Not benchmarked | $1.07 | |
| 81 | Ministral 3 3B 2512Mistral AI | 0.8 | Not benchmarked | $0.10 | |
| 82 | Mistral Small 4Mistral AI | 0.8 | Not benchmarked | $0.60 | |
| 83 | Llama 4 MaverickMeta Llama | 0.6 | Not benchmarked | $1.00 | |
| 84 | Ministral 3 8B 2512Mistral AI | 0.6 | Not benchmarked | $0.15 | |
| 85 | Llama 4 ScoutMeta Llama | 0.5 | Not benchmarked | $0.50 | |
| 86 | Gemma 3 12BGoogle | 0.1 | Not benchmarked | $0.1625 | |
| 87 | Gemma 3 27BGoogle | 0.1 | Not benchmarked | $0.30 |
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.