benchgap
Other · model

Jais-3-32B benchmark scores

As of 2026-10-29, Jais-3-32B (Other) has measured scores on 2 benchmarks and estimated scores on 17 more.

BenchmarkScoreSource
AA-SciCode44.8%estimated ± 3.9 pp, high confidence
SciCode44.5%estimated ± 3.3 pp, high confidence
Terminal-Bench 2.163.7%measured
AA Coding Index44.6%estimated ± 5.3 pp, medium confidence
SWE-bench Verified72.4%measured
SWE-bench Pro49.9%estimated ± 4.6 pp, high confidence
AA Terminal-Bench 2.169.9%estimated ± 6.8 pp, low confidence
Terminal-Bench 3.06.2%estimated ± 9.1 pp, low confidence
FrontierCode 1.1 Main6.2%estimated ± 2.7 pp, low confidence
Vals LiveCodeBench72.0%estimated ± 9.9 pp, low confidence
Vals SWE-bench65.9%estimated ± 6.8 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)55.2%estimated ± 7.4 pp, medium confidence
AA Terminal-Bench 4.05.1%estimated ± 11.6 pp, low confidence
DeepSWE29.9%estimated ± 12.7 pp, low confidence
Vibe Code Bench1.0%estimated ± 8.1 pp, medium confidence
NL2Repo30.4%estimated ± 6.2 pp, medium confidence
React Native Evals72.3%estimated ± 2.3 pp, medium confidence
SWE-Rebench57.0%estimated ± 3.6 pp, medium confidence
LiveCodeBench74.6%estimated ± 14.6 pp, low confidence