Other · model
BTL-4 benchmark scores
As of 2026-11-21, BTL-4 (Other) has measured scores on 3 benchmarks and estimated scores on 18 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-SciCode | 47.7% | estimated ± 3.8 pp, high confidence |
| GDPval-AA | 21.4% | estimated ± 5.5 pp, medium confidence |
| LiveCodeBench v6 | 66.1% | measured |
| SciCode | 46.9% | estimated ± 3.6 pp, high confidence |
| τ²-bench results | 92.9% | estimated ± 12.4 pp, low confidence |
| AA Coding Index | 57.6% | estimated ± 5.3 pp, medium confidence |
| SWE-bench Verified | 78.4% | measured |
| BFCL v4 | 73.5% | measured |
| SWE-bench Pro | 56.7% | estimated ± 4.5 pp, high confidence |
| Vals LiveCodeBench | 79.9% | estimated ± 10.0 pp, low confidence |
| FrontierCode 1.1 Main | 24.7% | estimated ± 4.2 pp, low confidence |
| Vals SWE-bench | 74.0% | estimated ± 6.6 pp, medium confidence |
| DeepSWE | 45.0% | estimated ± 12.7 pp, low confidence |
| Vibe Code Bench | 26.0% | estimated ± 8.4 pp, medium confidence |
| MCP Atlas | 73.7% | estimated ± 14.2 pp, low confidence |
| NL2Repo | 42.4% | estimated ± 6.2 pp, medium confidence |
| PostTrainBench v1 | 17.2% | estimated ± 5.5 pp, low confidence |
| React Native Evals | 78.9% | estimated ± 2.7 pp, medium confidence |
| SWE-Rebench | 61.6% | estimated ± 3.6 pp, medium confidence |
| LiveCodeBench | 78.3% | estimated ± 14.6 pp, low confidence |
| PinchBench | 100.0% | estimated ± 5.0 pp, low confidence |