Artificial Analysis Agentic Index
Indexes · 2025-09-02
Composite index of tool use, planning, autonomy, and agentic workflows.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 55.3 |
| GPT-5.6 Sol | 54.0 |
| Claude Fable 5 | 52.8 |
| Kimi K3 | 50.1 |
| GPT-5.6 Terra | 47.4 |
| Opus 4.8 | 47.2 |
| Sonnet 5 | 46.7 |
| Grok 4.5 | 45.7 |
| DeepSeek-V4-Flash-0731 | 45.7 |
| GPT-5.6 Luna | 45.6 |
| GPT-5.5 | 44.9 |
| Opus 4.7 | 44.4 |
| GLM-5.2 | 43.1 |
| GPT-5.4 | 41.1 |
| Sonnet 4.6 | 40.8 |
| Gemini 3.6 Flash | 38.7 |
| Muse Spark 1.1 | 37.5 |
| Gemini 3.5 Flash | 37.4 |
| DeepSeek-V4-Pro | 36.4 |
| MiniMax M3 | 35.4 |
| Motif-3-Beta | 34.9 |
| JT-4.1 Flash 236B A21B | 34.9 |
| Inkling | 32.3 |
| DeepSeek-V4-Flash | 31.1 |
| Nex-N2-Pro | 31.0 |
| Inkling-Small | 30.8 |
| Hy3 | 30.7 |
| Qwen3.7-Max | 30.6 |
| Kimi K2.6 | 30.3 |
| GPT-5.4 Mini | 30.2 |
| GLM-5.1 | 29.9 |
| Kimi K2.7 Code | 29.6 |
| MiMo-V2.5-Pro | 29.1 |
| Muse Spark | 28.7 |
| Grok Build 0.1 | 28.0 |
| Qwen3.6 Plus (2026-04-02) | 27.6 |
| GPT-5.4 Nano | 27.5 |
| Nemotron 3 Ultra 550B A55B | 27.4 |
| Qwen3.6 27B | 27.0 |
| Gemini 3.5 Flash-Lite | 26.8 |