benchgap
Other · model

MAI-Code-1.1-Flash benchmark scores

As of 2026-10-07, MAI-Code-1.1-Flash (Other) has measured scores on 2 benchmarks and estimated scores on 16 more.

BenchmarkScoreSource
AA-SciCode44.8%estimated ± 3.9 pp, high confidence
LiveCodeBench v685.1%estimated ± 8.1 pp, low confidence
SciCode45.0%estimated ± 3.8 pp, high confidence
Terminal-Bench 2.162.9%measured
AA Coding Index45.8%estimated ± 5.1 pp, medium confidence
SWE-bench Verified72.6%measured
SWE-bench Pro47.8%estimated ± 3.2 pp, high confidence
Terminal-Bench 3.06.0%estimated ± 9.1 pp, low confidence
FrontierCode 1.1 Main6.5%estimated ± 2.7 pp, low confidence
Vals LiveCodeBench72.3%estimated ± 9.9 pp, low confidence
Vals SWE-bench66.2%estimated ± 6.8 pp, medium confidence
Terminal-Bench 2.1 (Vals AI)54.5%estimated ± 7.4 pp, medium confidence
AA Terminal-Bench 2.156.5%estimated ± 3.5 pp, high confidence
AA Terminal-Bench 4.00.0%estimated ± 8.9 pp, medium confidence
Vibe Code Bench1.0%estimated ± 8.1 pp, medium confidence
NL2Repo32.6%estimated ± 6.1 pp, medium confidence
SWE-Rebench57.0%estimated ± 3.6 pp, medium confidence
LiveCodeBench81.8%estimated ± 10.2 pp, low confidence