benchgap
Other · model

Pareto 26.10 Preview benchmark scores

As of 2026-11-22, Pareto 26.10 Preview (Other) has measured scores on 3 benchmarks and estimated scores on 38 more.

BenchmarkScoreSource
AA-GPQA Diamond92.0%estimated ± 4.4 pp, high confidence
AA-HLE41.8%estimated ± 3.9 pp, high confidence
AA-SciCode57.7%estimated ± 3.9 pp, medium confidence
Artificial Analysis Intelligence Index36.9%estimated ± 9.8 pp, medium confidence
CritPt18.1%estimated ± 4.6 pp, high confidence
GPQA Diamond92.4%measured
HLE47.7%estimated ± 6.8 pp, medium confidence
AA-Omniscience Accuracy41.4%estimated ± 8.4 pp, medium confidence
SciCode59.5%estimated ± 7.6 pp, low confidence
Terminal-Bench 2.188.2%estimated ± 6.5 pp, low confidence
AA Coding Index76.1%estimated ± 2.5 pp, high confidence
SWE-bench Verified88.1%estimated ± 5.1 pp, medium confidence
SWE-bench Pro73.0%estimated ± 7.7 pp, medium confidence
MMLU-Pro88.8%estimated ± 5.4 pp, medium confidence
GPQA92.4%estimated ± 0.0 pp, high confidence
Vals GPQA Diamond91.5%estimated ± 2.1 pp, high confidence
Vals MMLU-Pro87.9%estimated ± 1.6 pp, high confidence
MMMLU90.6%estimated ± 1.1 pp, medium confidence
ARC-AGI-192.8%estimated ± 2.5 pp, high confidence
ARC-AGI-270.1%estimated ± 9.7 pp, medium confidence
CursorBench 3.267.6%estimated ± 6.4 pp, low confidence
FrontierCode 1.1 Main49.8%estimated ± 3.5 pp, low confidence
Terminal-Bench 4.151.4%estimated ± 4.6 pp, high confidence
Bug Hunt Bench31.9%estimated ± 10.4 pp, low confidence
DeepSWE69.9%measured
FrontierCode 2.032.0%estimated ± 10.2 pp, low confidence
HLE w/o tools42.0%estimated ± 4.3 pp, high confidence
PostTrainBench v1.137.8%estimated ± 4.5 pp, high confidence
Terminal-Bench 4.050.8%measured
Terminal-Bench-Science 0.142.0%estimated ± 14.2 pp, low confidence
VulcanBench Frontier v487.1%estimated ± 5.0 pp, high confidence
AA Terminal-Bench 4.047.5%estimated ± 6.3 pp, medium confidence
ARC-AGI-30.0%estimated ± 8.6 pp, medium confidence
MMLU-Redux92.9%estimated ± 2.8 pp, high confidence
NL2Repo60.8%estimated ± 6.0 pp, medium confidence
SuperGPQA80.2%estimated ± 13.9 pp, low confidence
MedXpertQA (Text)61.7%estimated ± 4.5 pp, medium confidence
MMLU-Pro (Arcee)87.7%estimated ± 3.4 pp, low confidence
HealthBench Professional55.8%estimated ± 4.2 pp, medium confidence
ScarfBench66.6%estimated ± 3.8 pp, medium confidence
SWE-Atlas Codebase QnA60.6%estimated ± 4.8 pp, high confidence