Other · model
Ember-1 benchmark scores
As of 2026-10-07, Ember-1 (Other) has measured scores on 3 benchmarks and estimated scores on 18 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-SciCode | 53.6% | estimated ± 3.9 pp, high confidence |
| LiveCodeBench v6 | 87.1% | estimated ± 8.1 pp, low confidence |
| SciCode | 53.9% | estimated ± 3.8 pp, medium confidence |
| Terminal-Bench 2.1 | 82.0% | measured |
| AA Coding Index | 77.8% | estimated ± 2.5 pp, high confidence |
| SWE-bench Verified | 92.2% | measured |
| SWE-bench Pro | 74.7% | estimated ± 3.2 pp, high confidence |
| CursorBench 3.2 | 68.2% | estimated ± 6.4 pp, low confidence |
| Terminal-Bench 3.0 | 15.1% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 51.6% | estimated ± 2.7 pp, medium confidence |
| Vals LiveCodeBench | 91.8% | estimated ± 9.9 pp, low confidence |
| Vals SWE-bench | 93.1% | estimated ± 6.8 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 69.3% | estimated ± 7.4 pp, medium confidence |
| AA Terminal-Bench 2.1 | 84.8% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 21.0% | estimated ± 8.9 pp, medium confidence |
| DeepSWE | 75.2% | measured |
| PostTrainBench v1.1 | 43.7% | estimated ± 4.8 pp, high confidence |
| Vibe Code Bench | 62.5% | estimated ± 8.1 pp, low confidence |
| NL2Repo | 71.2% | estimated ± 6.1 pp, low confidence |
| SWE-Rebench | 61.8% | estimated ± 3.6 pp, low confidence |
| LiveCodeBench | 93.5% | estimated ± 10.2 pp, low confidence |