Other · model
SWE-2 benchmark scores
As of 2026-10-07, SWE-2 (Other) has measured scores on 4 benchmarks and estimated scores on 14 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-SciCode | 58.5% | estimated ± 3.8 pp, medium confidence |
| Terminal-Bench 2.1 | 92.8% | measured |
| AA Coding Index | 77.1% | estimated ± 2.5 pp, high confidence |
| SWE-bench Verified | 91.8% | estimated ± 0.8 pp, medium confidence |
| SWE-bench Pro | 76.6% | estimated ± 7.5 pp, medium confidence |
| CursorBench 3.2 | 66.7% | estimated ± 1.6 pp, medium confidence |
| Terminal-Bench 3.0 | 36.4% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 50.0% | measured |
| Vals LiveCodeBench | 88.1% | estimated ± 1.9 pp, high confidence |
| Vals SWE-bench | 90.9% | estimated ± 2.8 pp, high confidence |
| Terminal-Bench 2.1 (Vals AI) | 76.2% | estimated ± 4.6 pp, medium confidence |
| AA Terminal-Bench 2.1 | 84.9% | estimated ± 3.5 pp, medium confidence |
| AA Terminal-Bench 4.0 | 24.8% | estimated ± 4.7 pp, high confidence |
| DeepSWE | 73.0% | measured |
| PostTrainBench v1.1 | 41.6% | estimated ± 4.8 pp, high confidence |
| Terminal-Bench 4.0 | 27.3% | measured |
| Vibe Code Bench | 78.2% | estimated ± 5.6 pp, low confidence |
| NL2Repo | 60.9% | estimated ± 6.6 pp, medium confidence |