Other · model
MAI Code 2 benchmark scores
As of 2026-11-18, MAI Code 2 (Other) has measured scores on 2 benchmarks and estimated scores on 18 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-SciCode | 58.5% | estimated ± 3.9 pp, medium confidence |
| SciCode | 61.0% | estimated ± 7.6 pp, low confidence |
| Terminal-Bench 2.1 | 84.6% | measured |
| AA Coding Index | 77.1% | estimated ± 2.5 pp, high confidence |
| SWE-bench Verified | 89.6% | estimated ± 5.4 pp, medium confidence |
| SWE-bench Pro | 82.8% | estimated ± 7.7 pp, medium confidence |
| AA Terminal-Bench 2.1 | 82.4% | estimated ± 2.6 pp, high confidence |
| CursorBench 3.2 | 68.0% | estimated ± 6.4 pp, low confidence |
| Terminal-Bench 3.0 | 17.8% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 51.5% | estimated ± 3.5 pp, low confidence |
| Terminal-Bench 4.1 | 21.6% | estimated ± 10.9 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 71.1% | estimated ± 7.3 pp, medium confidence |
| Bug Hunt Bench | 35.5% | estimated ± 10.4 pp, low confidence |
| DeepSWE | 73.2% | measured |
| PostTrainBench v1.1 | 41.3% | estimated ± 4.5 pp, high confidence |
| VulcanBench Frontier v4 | 89.3% | estimated ± 5.0 pp, high confidence |
| AA Terminal-Bench 4.0 | 8.2% | estimated ± 11.0 pp, low confidence |
| NL2Repo | 62.2% | estimated ± 6.0 pp, medium confidence |
| ScarfBench | 68.2% | estimated ± 3.8 pp, medium confidence |
| SWE-Atlas Codebase QnA | 61.3% | estimated ± 4.8 pp, high confidence |