Loading data...
Artificial Analysis: leaderboard
Composite Intelligence Index (v4.0) aggregating 10 evaluations across Agents, Coding, General, and Scientific Reasoning - independently run by Artificial Analysis on 280+ models.
Metric: Intelligence Index. Source: artificialanalysis.ai. Status: years away from saturation. 630 models tracked.
Top models
| # | Model | Score |
|---|
| 1 | Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) | 56.76 |
| 2 | GPT-6 (Max) | 54.66 |
| 3 | GPT-6 (xHigh) | 54.31 |
| 4 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 54.05 |
| 5 | Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) | 53.8 |
| 6 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | 53.37 |
| 7 | GPT-6 (High) | 53.36 |
| 8 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | 53.19 |
| 9 | Muse Spark 1.3 (Max) | 52.95 |
| 10 | GPT-6 (Medium) | 52.25 |
| 11 | Claude Opus 5 (Adaptive Reasoning, High Effort) | 52.03 |
| 12 | Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) | 51.67 |
| 13 | Muse Spark 1.3 (xHigh) | 51.55 |
| 14 | GPT-5.6 Sol (Max) | 51.26 |
| 15 | Grok 4.6 (High) | 50.58 |
Interactive version: theaggregate.ai/benchmark?slug=artificial-analysis · How It Works · Data refreshed daily, snapshot 2026-09-05.