Other · model
Composer 2 benchmark scores
As of 2026-10-07, Composer 2 (Other) has measured scores on 4 benchmarks and estimated scores on 9 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-SciCode | 56.6% | estimated ± 8.6 pp, low confidence |
| AA Coding Index | 88.9% | estimated ± 11.4 pp, low confidence |
| SWE-bench Verified | 75.7% | estimated ± 4.8 pp, medium confidence |
| Vals LiveCodeBench | 89.4% | estimated ± 3.8 pp, low confidence |
| Vals SWE-bench | 88.1% | estimated ± 1.4 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 54.1% | estimated ± 6.3 pp, medium confidence |
| SWE Multilingual | 73.7% | measured |
| Vibe Code Bench | 66.5% | estimated ± 6.5 pp, low confidence |
| MMLU-ProX | 84.3% | estimated ± 1.7 pp, medium confidence |
| NOVA-63 | 56.6% | estimated ± 1.6 pp, low confidence |
| Terminal-Bench 2.0 | 61.7% | measured |
| React Native Evals | 96.1% | measured |
| SWE-Rebench | 58.0% | measured |