benchgap
Other · model

Pareto 26.9 benchmark scores

As of 2026-11-22, Pareto 26.9 (Other) has measured scores on 4 benchmarks and estimated scores on 62 more.

BenchmarkScoreSource
AA-GPQA Diamond92.0%estimated ± 2.7 pp, high confidence
AA-HLE47.8%estimated ± 4.6 pp, high confidence
AA-SciCode58.6%estimated ± 3.9 pp, medium confidence
Artificial Analysis Intelligence Index40.1%estimated ± 5.6 pp, medium confidence
CritPt21.9%estimated ± 5.5 pp, medium confidence
GPQA Diamond95.1%estimated ± 2.0 pp, high confidence
HLE56.4%estimated ± 6.5 pp, medium confidence
AA-Omniscience Accuracy48.5%estimated ± 7.7 pp, medium confidence
SciCode61.4%estimated ± 7.6 pp, low confidence
Terminal-Bench 2.188.2%estimated ± 6.5 pp, low confidence
AA Coding Index77.4%estimated ± 2.5 pp, high confidence
AA-MMMU-Pro77.1%estimated ± 1.5 pp, high confidence
SWE-bench Verified90.0%estimated ± 5.1 pp, medium confidence
SWE-bench Pro85.7%estimated ± 7.7 pp, medium confidence
MMLU-Pro85.8%estimated ± 2.5 pp, low confidence
GPQA93.8%estimated ± 3.2 pp, high confidence
Vals GPQA Diamond92.3%estimated ± 2.9 pp, high confidence
Vals MMLU-Pro89.7%estimated ± 1.8 pp, high confidence
MMMU84.9%estimated ± 1.7 pp, high confidence
ARC-AGI-195.8%estimated ± 3.9 pp, high confidence
ARC-AGI-280.0%estimated ± 13.0 pp, low confidence
CursorBench 3.268.1%estimated ± 6.4 pp, low confidence
FrontierCode 1.1 Main51.9%estimated ± 3.5 pp, low confidence
ParseBench-161.4%estimated ± 8.4 pp, medium confidence
Terminal-Bench 4.151.6%estimated ± 4.6 pp, high confidence
HealthBench Professional (length-adjusted, Artificial Analysis)58.4%estimated ± 4.4 pp, medium confidence
HealthBench Professional (raw, Artificial Analysis)66.8%estimated ± 2.6 pp, medium confidence
Bug Hunt Bench36.4%estimated ± 10.4 pp, low confidence
DeepSWE74.0%measured
FrontierCode 2.032.3%estimated ± 10.2 pp, low confidence
HLE w/o tools49.0%measured
PostTrainBench v1.142.2%estimated ± 4.5 pp, high confidence
Terminal-Bench 4.051.0%measured
Terminal-Bench-Science 0.142.4%estimated ± 14.2 pp, low confidence
VulcanBench Frontier v489.8%estimated ± 5.0 pp, high confidence
AA Terminal-Bench 4.047.7%estimated ± 6.3 pp, medium confidence
ARC-AGI-310.2%estimated ± 7.2 pp, medium confidence
ParseBench-269.1%estimated ± 5.0 pp, medium confidence
CharXiv80.5%estimated ± 5.6 pp, medium confidence
CharXiv w/o tools82.1%estimated ± 1.2 pp, high confidence
AI2D_TEST92.3%estimated ± 2.0 pp, medium confidence
CountBench95.0%estimated ± 3.0 pp, high confidence
DynaMath84.9%estimated ± 5.3 pp, low confidence
ERQA61.9%estimated ± 6.4 pp, medium confidence
MathVision87.3%estimated ± 3.0 pp, high confidence
MLVU (M-Avg)85.9%estimated ± 2.2 pp, high confidence
MMMU-Pro78.0%measured
NL2Repo62.5%estimated ± 6.0 pp, medium confidence
RealWorldQA83.6%estimated ± 2.8 pp, high confidence
ScreenSpot Pro75.4%estimated ± 9.6 pp, low confidence
SimpleVQA66.3%estimated ± 7.5 pp, medium confidence
Video-MME (w/o subtitle)84.5%estimated ± 1.3 pp, high confidence
Video-MME (with subtitle)86.8%estimated ± 3.0 pp, high confidence
VideoMMMU85.4%estimated ± 2.4 pp, high confidence
We-Math82.2%estimated ± 7.4 pp, low confidence
MedXpertQA (MM)70.2%estimated ± 2.4 pp, high confidence
MedXpertQA (Text)66.1%estimated ± 8.9 pp, low confidence
HealthBench Professional57.1%estimated ± 4.2 pp, medium confidence
ScarfBench68.7%estimated ± 3.8 pp, medium confidence
BabyVision w/ Python88.8%estimated ± 3.8 pp, low confidence
BabyVision60.8%estimated ± 9.1 pp, low confidence
MMVU77.2%estimated ± 2.7 pp, medium confidence
PerceptionBench59.6%estimated ± 4.9 pp, low confidence
OCRBench V271.1%estimated ± 3.3 pp, high confidence
MMMU-Pro w/ Python80.6%estimated ± 2.6 pp, high confidence
SWE-Atlas Codebase QnA61.5%estimated ± 4.8 pp, high confidence