Live AI model rankings across intelligence, speed and cost — 129 datasets, updated daily. Current leader of Artificial Analysis Intelligence Index by Open Weights / Proprietary: .
| # | Entry | Creator | Value | Δ vs #1 |
|---|---|---|---|---|
| 1 | Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) | Anthropic | 53.4 | 0.0% |
| 2 | GPT-6 Astra (max) | OpenAI | 52.8 | -1.0% |
| 3 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 50.7 | -5.0% |
| 4 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Anthropic | 49.7 | -6.9% |
| 5 | Muse Spark 1.3 (max) | Meta | 48.2 | -9.8% |
| 6 | GPT-5.6 Sol (max) | OpenAI | 47.1 | -11.8% |
| 7 | GLM-5.3 (max) | Z AI | 44.9 | -16.0% |
| 8 | Grok 4.6 (high) | SpaceXAI | 44.4 | -16.8% |
| 9 | Kimi K3 (max) | Kimi | 43.8 | -18.0% |
| 10 | GPT-5.6 Terra (max) | OpenAI | 42.3 | -20.8% |
| 11 | GLM-5.3-Flash | Z AI | 41.9 | -21.5% |
| 12 | Gemini 3.8 Flash (high) | 41.2 | -22.8% | |
| 13 | Qwen3.8 2.4T A95B | Alibaba | 40.0 | -25.0% |
| 14 | DeepSeek V4.1 Flash (Reasoning, Max Effort) | DeepSeek | 39.5 | -25.9% |
| 15 | GPT-5.6 Luna (max) | OpenAI | 37.5 | -29.7% |
| 16 | DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | DeepSeek | 36.3 | -32.0% |
| 17 | Qwen3.8 27B (xhigh) | Alibaba | 33.9 | -36.5% |
| 18 | K2 Horizon 375B A23B | MBZUAI Institute of Foundation Models | 30.8 | -42.3% |
| 19 | MiniMax-M3 | MiniMax | 29.6 | -44.5% |
| 20 | Inkling (xhigh) | Thinking Machines | 25.5 | -52.1% |