# Artificial Analysis Agentic Index (AA Agentic Index)

> A display-only Artificial Analysis agentic index.

Canonical page: https://benchlm.ai/benchmarks/aaagenticindex

- Category: [Agentic](/agentic)
- Last updated: September 10, 2026

## About AA Agentic Index

- Year: 2026
- Tasks: Cross-benchmark agentic index
- Format: Aggregated model score
- Difficulty: Display-only external reference
- Paper: [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models)

BenchLM mirrors this agentic index for comparison, but does not use it as a weighted agentic benchmark row.

AA Agentic Index is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (72 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | 58.0% |
| 2 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | 56.2% |
| 3 | [Muse Spark 1.3](/models/muse-spark-1-3) | Meta | 55.7% |
| 4 | [GLM-5.3](/models/glm-5-3) | Z.AI | 53.4% |
| 5 | [Grok 4.6](/models/grok-4-6) | xAI | 53.4% |
| 6 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | 51.5% |
| 7 | [Claude Fable 5](/models/claude-fable) | Anthropic | 51.0% |
| 8 | [Kimi K3](/models/kimi-k3) | Moonshot AI | 50.6% |
| 9 | [GPT-5.6 Sol](/models/gpt-5-6-sol) | OpenAI | 50.5% |
| 10 | [Qwen3.8 Max Preview](/models/qwen3-8-max-preview) | Alibaba | 49.6% |
| 11 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | DeepSeek | 49.6% |
| 12 | [Qwen3.8-27B](/models/qwen3-8-27b) | Alibaba | 46.5% |
| 13 | [Claude Sonnet 5](/models/claude-sonnet-5) | Anthropic | 44.3% |
| 14 | [Muse Spark 1.2](/models/muse-spark-1-2) | Meta | 44.0% |
| 15 | [GPT-5.6 Terra](/models/gpt-5-6-terra) | OpenAI | 43.7% |
| 16 | [GPT-5.6 Luna](/models/gpt-5-6-luna) | OpenAI | 42.7% |
| 17 | [Claude Opus 4.8](/models/claude-opus-4-8) | Anthropic | 42.6% |
| 18 | [Grok 4.5](/models/grok-4-5) | xAI | 42.1% |
| 19 | [DeepSeek V4 Flash 0731](/models/deepseek-v4-flash-0731) | DeepSeek | 41.7% |
| 20 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | Google | 41.1% |
| 21 | [Claude Opus 4.7 (Adaptive)](/models/claude-opus-4-7-adaptive) | Anthropic | 39.5% |
| 22 | [GLM-5.2](/models/glm-5-2) | Z.AI | 39.4% |
| 23 | [GPT-5.5](/models/gpt-5-5) | OpenAI | 37.3% |
| 24 | [Gemini 3.7 Flash](/models/gemini-3-7-flash) | Google | 36.4% |
| 25 | [Quasar 438B](/models/quasar-438b) | Multiverse Computing | 32.7% |
| 26 | [MiniMax M3](/models/minimax-m3) | MiniMax | 30.8% |
| 27 | [Gemini 3.6 Flash](/models/gemini-3-6-flash) | Google | 30.1% |
| 28 | [Muse Spark 1.1](/models/muse-spark-1-1) | Meta | 27.5% |
| 29 | [Gemini 3.5 Flash](/models/gemini-3-5-flash) | Google | 27.3% |
| 30 | [Hy3](/models/hy3) | Tencent | 25.6% |
| 31 | [Hy3 Preview](/models/hy3-preview) | Tencent | 25.6% |
| 32 | [GLM-5.1](/models/glm-5-1) | Z.AI | 25.2% |
| 33 | [Inkling-Small](/models/inkling-small) | Thinking Machines Lab | 24.9% |
| 34 | [Inkling](/models/inkling) | Thinking Machines Lab | 24.3% |
| 35 | [Qwen3.7 Max](/models/qwen3-7-max) | Alibaba | 23.9% |
| 36 | [MiMo-V2.5-Pro](/models/mimo-v2-5-pro) | Xiaomi | 22.7% |
| 37 | [Kimi K2.7 Code](/models/kimi-k2-7-code) | Moonshot AI | 22.5% |
| 38 | [Kimi K2.6](/models/kimi-2-6) | Moonshot AI | 22.1% |
| 39 | [Nemotron 3 Ultra](/models/nemotron-3-ultra) | NVIDIA | 21.7% |
| 40 | [Ling 3.0 Flash](/models/ling-3-0-flash) | InclusionAI | 21.0% |
| 41 | [Ling 3.0 Flash FP8](/models/ling-3-0-flash-fp8) | InclusionAI | 21.0% |
| 42 | [Qwen3.6-27B](/models/qwen3-6-27b) | Alibaba | 20.1% |
| 43 | [Qwen3.7 Plus](/models/qwen3-7-plus) | Alibaba | 19.7% |
| 44 | [GPT-5.4 mini](/models/gpt-5-4-mini) | OpenAI | 19.6% |
| 45 | [GPT-5.4 nano](/models/gpt-5-4-nano) | OpenAI | 17.7% |
| 46 | [Grok 4.3](/models/grok-4-3) | xAI | 17.2% |
| 47 | [MiniMax M2.7](/models/minimax-m2-7) | MiniMax | 16.8% |
| 48 | [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) | Google | 15.9% |
| 49 | [Qwen3.6-35B-A3B](/models/qwen3-6-35b-a3b) | Alibaba | 15.0% |
| 50 | [Muse Glimmer 30B](/models/muse-glimmer-30b) | Meta | 10.5% |
| 51 | [Gemini 3.1 Pro](/models/gemini-3-1-pro) | Google | 10.3% |
| 52 | [Qwen3.5-122B-A10B](/models/qwen3-5-122b-a10b) | Alibaba | 9.6% |
| 53 | [Mistral Medium 3.5 128B](/models/mistral-medium-3-5-128b) | Mistral | 9.3% |
| 54 | [Gemma 4 31B](/models/gemma-4-31b) | Google | 6.7% |
| 55 | [GPT-OSS 120B](/models/gpt-oss-120b) | OpenAI | 6.2% |
| 56 | [Nemotron 3.5 Lightning 30B A3B NVFP4](/models/nemotron-3-5-lightning-30b-a3b-nvfp4) | NVIDIA | 6.1% |
| 57 | [Nemotron 3 Super 100B](/models/nemotron-3-super-100b) | NVIDIA | 4.1% |
| 58 | [Granite 4.2 8B](/models/granite-4-2-8b) | IBM | 3.7% |
| 59 | [Command A+](/models/command-a-plus) | Cohere | 3.6% |
| 60 | [Gemini 2.5 Pro](/models/gemini-2-5-pro) | Google | 3.5% |
| 61 | [Mistral Large 3](/models/mistral-large-3) | Mistral | 2.4% |
| 62 | [Mistral Small 4](/models/mistral-small-4) | Mistral | 1.4% |
| 63 | [Mistral Small 4 (Reasoning)](/models/mistral-small-4-reasoning) | Mistral | 1.4% |
| 64 | [GPT-OSS 20B](/models/gpt-oss-20b) | OpenAI | 1.4% |
| 65 | [Trinity-Large-Preview](/models/trinity-large-preview) | Arcee AI | 1.2% |
| 66 | [Trinity-Large-Thinking](/models/trinity-large-thinking) | Arcee AI | 1.2% |
| 67 | [Nemotron 3 Nano 30B](/models/nemotron-3-nano-30b) | NVIDIA | 1.0% |
| 68 | [DeepSeek V3](/models/deepseek-v3) | DeepSeek | 0.8% |
| 69 | [Celeris-1](/models/celeris-1) | Celeris | 0.7% |
| 70 | [Llama 4 Maverick](/models/llama-4-maverick) | Meta | 0.6% |
| 71 | [Llama 4 Scout](/models/llama-4-scout) | Meta | 0.6% |
| 72 | [Gemma 3 27B](/models/gemma-3-27b) | Google | 0.1% |

## FAQ

### What does AA Agentic Index measure?

A display-only Artificial Analysis agentic index.

### Which model scores highest on AA Agentic Index?

Claude Fable 5.1 by Anthropic currently leads with a score of 58.0% on AA Agentic Index.

### How many models are evaluated on AA Agentic Index?

72 AI models have been evaluated on AA Agentic Index on BenchLM.

### Does AA Agentic Index affect BenchLM's overall score?

Not directly. AA Agentic Index is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on AA Agentic Index

- [Claude Fable 5.1 vs Claude Opus 5](/compare/claude-fable-5-1-vs-claude-opus-5)
- [Claude Opus 5 vs Muse Spark 1.3](/compare/claude-opus-5-vs-muse-spark-1-3)
- [Muse Spark 1.3 vs GLM-5.3](/compare/glm-5-3-vs-muse-spark-1-3)
- [GLM-5.3 vs Grok 4.6](/compare/glm-5-3-vs-grok-4-6)