Other · model
Jais-3-7B benchmark scores
As of 2026-10-29, Jais-3-7B (Other) has measured scores on 2 benchmarks and estimated scores on 17 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-SciCode | 43.7% | estimated ± 3.9 pp, high confidence |
| SciCode | 43.4% | estimated ± 3.3 pp, high confidence |
| Terminal-Bench 2.1 | 46.4% | measured |
| AA Coding Index | 40.4% | estimated ± 5.3 pp, medium confidence |
| SWE-bench Verified | 70.2% | measured |
| SWE-bench Pro | 47.5% | estimated ± 4.6 pp, high confidence |
| AA Terminal-Bench 2.1 | 56.3% | estimated ± 6.8 pp, low confidence |
| Terminal-Bench 3.0 | 3.1% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 3.8% | estimated ± 2.7 pp, low confidence |
| Vals LiveCodeBench | 68.1% | estimated ± 9.9 pp, low confidence |
| Vals SWE-bench | 62.9% | estimated ± 6.8 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 41.8% | estimated ± 7.4 pp, low confidence |
| AA Terminal-Bench 4.0 | 0.8% | estimated ± 11.6 pp, low confidence |
| DeepSWE | 26.0% | estimated ± 12.7 pp, low confidence |
| Vibe Code Bench | 0.7% | estimated ± 8.1 pp, medium confidence |
| NL2Repo | 26.4% | estimated ± 6.2 pp, medium confidence |
| React Native Evals | 71.8% | estimated ± 2.3 pp, medium confidence |
| SWE-Rebench | 57.0% | estimated ± 3.6 pp, medium confidence |
| LiveCodeBench | 73.1% | estimated ± 14.6 pp, low confidence |