Benchmark Leaderboards
Loading leaderboardsβ¦
Loading leaderboardsβ¦
Track which models hold the current SOTA on the benchmarks the field actually uses. Click a column header to sort; the leading row is highlighted.
The Artificial Analysis Intelligence Index β the field's most-cited cross-model aggregate, a composite of GPQA Diamond, MMLU-Pro, AIME, LiveCodeBench, HLE and more across frontier closed + open-weight models. Higher is better.
Metric: Intelligence Index β higher is better Β· Source β
| # β² | Model / Paper | Intelligence Index | Ξ vs SOTA | Links |
|---|---|---|---|---|
| 1 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)SOTA | 59.9 | β | search β |
| 2 | GPT-5.6 Sol (max) | 58.9 | -1.00 | search β |
| 3 | GPT-5.6 Sol (xhigh) | 57.7 | -2.20 | search β |
| 4 | GPT-5.6 Sol (high) | 55.9 | -4.00 | search β |
| 5 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 55.7 | -4.20 | search β |
| 6 | GPT-5.6 Terra (max) | 55 | -4.90 | search β |
| 7 | GPT-5.5 (xhigh) | 54.8 | -5.10 | search β |
| 8 | Grok 4.5 (high) | 53.8 | -6.10 | search β |
| 9 | GPT-5.6 Sol (medium) | 53.6 | -6.30 | search β |
| 10 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | 53.5 | -6.40 | search β |
| 11 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | 53.4 | -6.50 | search β |
| 12 | GPT-5.5 (high) | 53.1 | -6.80 | search β |
| 13 | GPT-5.6 Terra (xhigh) | 51.6 | -8.30 | search β |
| 14 | GPT-5.4 (xhigh) | 51.4 | -8.50 | search β |
| 15 | GPT-5.6 Luna (max) | 51.2 | -8.70 | search β |
| 16 | GLM-5.2 (max) | 51.1 | -8.80 | search β |
| 17 | Muse Spark 1.1 (xhigh) | 50.6 | -9.30 | search β |
| 18 | GPT-5.5 (medium) | 50.4 | -9.50 | search β |
| 19 | Gemini 3.5 Flash (high) | 50.2 | -9.70 | search β |
| 20 | GPT-5.6 Sol (low) | 49.4 | -10.50 | search β |
| 21 | GPT-5.6 Luna (xhigh) | 49.1 | -10.80 | search β |
| 22 | GPT-5.6 Terra (high) | 49 | -10.90 | search β |
| 23 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | 47.2 | -12.70 | search β |
| 24 | Gemini 3.1 Pro Preview | 46.5 | -13.40 | search β |
| 25 | GPT-5.6 Luna (high) | 46.1 | -13.80 | search β |
| 26 | Qwen3.7 Max | 46 | -13.90 | search β |
| 27 | GPT-5.6 Terra (medium) | 45.6 | -14.30 | search β |
| 28 | Gemini 3.5 Flash (medium) | 45.4 | -14.50 | search β |
| 29 | MiniMax-M3 | 44.4 | -15.50 | search β |
| 30 | GPT-5.3 Codex (xhigh) | 44.3 | -15.60 | search β |