Microsoft: mai-image-2.6
1 benchmarks
Leaderboard position
#66
Overall rank (of 1126 models)
2514
Elo rating
1
Benchmarks
Top 5.9%
Percentile
In Microsoft (of 19 models)
Above: HiDream: HiDream-O1-Image-1.5 #65
Below: Google: gemini-3.7-flash #67
Benchmark highlights
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 1 benchmarks
1/1
100.0%
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.
| Benchmark | Predicted | Confidence | Based on |
|---|---|---|---|
| ARC-Challenge | ~97.3 | 50% | — |
| ARC-Easy | ~94.8 | 50% | — |
| HellaSwag | ~95.4 | 50% | — |
| PIQA | ~84.39 | 50% | — |
| WinoGrande | ~92 | 50% | — |
| Humanity's Last Exam (no tools) | ~41.33 | 50% | — |
| Artificial Analysis Intelligence Index v5.0.1 | ~31.29 | 50% | — |
| MATH-500 | ~99.2 | 50% | — |
| AIME 2025 | ~100 | 50% | — |
| AIME 2026 | ~99.2 | 50% | — |
| HMMT Feb 2026 | ~96.9 | 50% | — |
| GPQA Diamond | ~94.86 | 50% | — |
| MMLU-Pro | ~90.53 | 50% | — |
| IFEval | ~96.75 | 50% | — |
| IFBench | ~80.86 | 50% | — |
| HumanEval | ~95.9 | 50% | — |
| MBPP | ~93.7 | 50% | — |
| Terminal-Bench v2.1 | ~78.98 | 50% | — |
| MMLU | ~92.5 | 50% | — |
| SWE-bench Verified | ~90.83 | 50% | — |
| SWE-bench Pro | ~66.5 | 50% | — |
| SciCode | ~52.79 | 50% | — |
| AA-LCR | ~75.51 | 50% | — |
| Humanity's Last Exam (with tools) | ~55.26 | 50% | — |
| GSM8K | ~99.6 | 50% | — |