benchgap
Other · model

Sakana Fugu benchmark scores

As of 2026-11-22, Sakana Fugu (Other) has measured scores on 10 benchmarks and estimated scores on 71 more.

BenchmarkScoreSource
AA-GPQA Diamond91.7%estimated ± 2.7 pp, high confidence
AA-HLE53.7%estimated ± 3.9 pp, high confidence
AA-SciCode58.7%estimated ± 3.0 pp, medium confidence
Artificial Analysis Intelligence Index38.1%estimated ± 5.6 pp, medium confidence
CritPt30.3%estimated ± 4.0 pp, high confidence
GPQA Diamond95.5%measured
HLE54.9%estimated ± 6.5 pp, medium confidence
AA-LCR74.1%estimated ± 3.4 pp, high confidence
LiveCodeBench v692.9%measured
AA-Omniscience Accuracy46.2%estimated ± 7.7 pp, medium confidence
SciCode60.1%measured
Terminal-Bench 2.180.2%measured
AA Coding Index67.3%estimated ± 5.7 pp, low confidence
AA-MMMU-Pro78.3%estimated ± 4.9 pp, medium confidence
SWE-bench Verified80.0%estimated ± 3.6 pp, high confidence
SWE-bench Pro59.0%measured
MMLU-Pro85.8%estimated ± 2.5 pp, low confidence
GPQA95.5%measured
MMLU88.1%estimated ± 4.2 pp, medium confidence
Vals GPQA Diamond94.3%estimated ± 2.1 pp, medium confidence
Vals LiveCodeBench88.8%estimated ± 0.8 pp, low confidence
Vals MMLU-Pro89.1%estimated ± 0.9 pp, medium confidence
MMMLU91.4%estimated ± 1.1 pp, low confidence
MMMU87.1%estimated ± 3.7 pp, low confidence
AA MMLU-Pro87.4%estimated ± 1.2 pp, low confidence
AA Terminal-Bench 2.181.7%estimated ± 2.6 pp, high confidence
ARC-AGI-196.7%estimated ± 2.5 pp, high confidence
ARC-AGI-287.1%estimated ± 9.7 pp, medium confidence
CursorBench 3.154.0%estimated ± 5.6 pp, low confidence
CursorBench 3.256.8%estimated ± 3.6 pp, high confidence
Terminal-Bench 3.013.6%estimated ± 9.1 pp, low confidence
FrontierCode 1.1 Main39.2%estimated ± 5.0 pp, high confidence
FrontierSWE v213.9%estimated ± 8.3 pp, medium confidence
ParseBench-162.1%estimated ± 8.6 pp, low confidence
Terminal-Bench 4.117.3%estimated ± 10.9 pp, low confidence
Vals SWE-bench78.0%estimated ± 5.3 pp, low confidence
Terminal-Bench 2.1 (Vals AI)67.7%estimated ± 7.3 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)58.2%estimated ± 4.4 pp, medium confidence
HealthBench Professional (raw, Artificial Analysis)66.2%estimated ± 2.6 pp, medium confidence
Bug Hunt Bench30.8%estimated ± 12.1 pp, low confidence
CursorBench 4.034.8%estimated ± 3.3 pp, medium confidence
DeepSWE66.4%estimated ± 8.4 pp, low confidence
FrontierCode 2.020.9%estimated ± 6.7 pp, medium confidence
HLE w/o tools47.2%measured
PostTrainBench v1.125.1%estimated ± 4.4 pp, high confidence
VulcanBench Frontier v479.1%estimated ± 8.3 pp, low confidence
AA Terminal-Bench 4.04.3%estimated ± 11.0 pp, low confidence
ARC-AGI-38.3%estimated ± 7.2 pp, medium confidence
CharXiv85.1%measured
CharXiv w/o tools79.2%estimated ± 2.4 pp, high confidence
AI2D_TEST93.5%estimated ± 0.9 pp, low confidence
C-Eval93.7%estimated ± 1.2 pp, medium confidence
CountBench97.1%estimated ± 3.7 pp, low confidence
DynaMath87.1%estimated ± 0.8 pp, low confidence
ERQA68.6%estimated ± 5.6 pp, medium confidence
MathVision88.4%estimated ± 3.3 pp, high confidence
MLVU (M-Avg)87.3%estimated ± 1.5 pp, high confidence
MMLU-Redux95.6%estimated ± 1.7 pp, medium confidence
MMMU-Pro79.7%estimated ± 3.1 pp, high confidence
NL2Repo43.8%estimated ± 2.8 pp, medium confidence
PostTrainBench v124.2%estimated ± 4.6 pp, high confidence
RealWorldQA85.5%estimated ± 1.5 pp, high confidence
ScreenSpot Pro79.3%estimated ± 6.8 pp, medium confidence
SuperGPQA82.8%estimated ± 8.5 pp, low confidence
Video-MME (with subtitle)88.7%estimated ± 2.9 pp, high confidence
VideoMMMU86.2%estimated ± 1.5 pp, medium confidence
We-Math84.6%estimated ± 7.9 pp, low confidence
HealthBench Hard36.6%estimated ± 5.1 pp, low confidence
LiveCodeBench Pro87.8%measured
MedXpertQA (MM)77.1%estimated ± 6.4 pp, low confidence
MedXpertQA (Text)75.1%estimated ± 4.5 pp, low confidence
MMLU-Pro (Arcee)88.7%estimated ± 3.4 pp, low confidence
PostTrainBench23.1%estimated ± 3.7 pp, high confidence
FrontierCode 1.1 Extended55.7%estimated ± 3.0 pp, low confidence
HealthBench Professional55.7%estimated ± 4.2 pp, medium confidence
SimpleQA38.6%estimated ± 13.4 pp, low confidence
OpenHarmony Bench v1.053.3%estimated ± 4.9 pp, low confidence
BabyVision67.7%estimated ± 11.5 pp, low confidence
MMVU78.5%estimated ± 3.6 pp, medium confidence
MRCRv286.6%measured
BioBasicsBench57.4%estimated ± 2.2 pp, medium confidence