Other · model
Sakana Fugu-Ultra benchmark scores
As of 2026-10-07, Sakana Fugu-Ultra (Other) has measured scores on 9 benchmarks and estimated scores on 52 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 92.2% | estimated ± 2.7 pp, high confidence |
| AA-HLE | 52.9% | estimated ± 4.0 pp, high confidence |
| AA-SciCode | 57.5% | estimated ± 3.1 pp, high confidence |
| Artificial Analysis Intelligence Index | 43.3% | estimated ± 5.1 pp, medium confidence |
| CritPt | 30.3% | estimated ± 4.1 pp, high confidence |
| GPQA Diamond | 95.5% | measured |
| HLE | 58.3% | estimated ± 5.7 pp, medium confidence |
| AA-LCR | 75.9% | estimated ± 4.5 pp, low confidence |
| LiveCodeBench v6 | 93.2% | measured |
| AA-Omniscience Accuracy | 58.1% | estimated ± 8.1 pp, medium confidence |
| SciCode | 58.7% | measured |
| Terminal-Bench 2.1 | 82.1% | measured |
| AA Coding Index | 67.5% | estimated ± 6.4 pp, low confidence |
| SWE-bench Verified | 91.1% | estimated ± 2.5 pp, high confidence |
| SWE-bench Pro | 73.7% | measured |
| MMLU-Pro | 85.8% | estimated ± 2.5 pp, low confidence |
| GPQA | 95.5% | measured |
| ARC-AGI-1 | 96.5% | estimated ± 2.7 pp, high confidence |
| ARC-AGI-2 | 91.5% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 63.2% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 69.1% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 15.2% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 47.1% | estimated ± 5.5 pp, medium confidence |
| FrontierSWE v2 | 39.5% | estimated ± 9.0 pp, medium confidence |
| Vals GPQA Diamond | 94.9% | estimated ± 2.0 pp, medium confidence |
| Vals LiveCodeBench | 88.5% | estimated ± 0.8 pp, low confidence |
| Vals MMLU-Pro | 88.8% | estimated ± 1.2 pp, medium confidence |
| Vals SWE-bench | 77.7% | estimated ± 5.3 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 69.4% | estimated ± 7.4 pp, medium confidence |
| AA Terminal-Bench 2.1 | 84.8% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 21.1% | estimated ± 8.9 pp, medium confidence |
| CursorBench 4.0 | 46.0% | estimated ± 3.6 pp, high confidence |
| HLE w/o tools | 50.0% | measured |
| PostTrainBench v1.1 | 34.9% | estimated ± 4.7 pp, high confidence |
| CharXiv | 86.6% | measured |
| CharXiv w/o tools | 79.2% | estimated ± 2.3 pp, high confidence |
| C-Eval | 96.1% | estimated ± 0.9 pp, low confidence |
| MathVision | 90.1% | estimated ± 2.6 pp, high confidence |
| MMLU-Redux | 95.2% | estimated ± 2.1 pp, medium confidence |
| MMMU-Pro | 80.5% | estimated ± 3.2 pp, high confidence |
| NL2Repo | 47.7% | estimated ± 3.1 pp, low confidence |
| ScreenSpot Pro | 82.0% | estimated ± 7.1 pp, medium confidence |
| SuperGPQA | 83.5% | estimated ± 9.2 pp, low confidence |
| VideoMMMU | 86.3% | estimated ± 1.5 pp, high confidence |
| ERQA | 69.5% | estimated ± 3.7 pp, high confidence |
| HealthBench Hard | 36.6% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 90.8% | measured |
| MedXpertQA (MM) | 77.7% | 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 |
| ARC-AGI-3 | 34.2% | estimated ± 2.1 pp, high confidence |
| FrontierCode 1.1 Extended | 59.9% | estimated ± 3.0 pp, medium confidence |
| HealthBench Professional | 60.7% | estimated ± 4.8 pp, medium confidence |
| OpenHarmony Bench | 60.9% | estimated ± 4.9 pp, low confidence |
| SimpleVQA | 70.1% | estimated ± 7.8 pp, low confidence |
| MMMLU | 91.4% | estimated ± 1.1 pp, low confidence |
| MMLU | 90.5% | estimated ± 3.6 pp, low confidence |
| MathVision w/ Python | 77.6% | estimated ± 0.9 pp, low confidence |
| RealWorldQA | 86.6% | estimated ± 1.1 pp, medium confidence |
| Video-MME (with subtitle) | 88.7% | estimated ± 0.9 pp, medium confidence |
| OmniDocBench 1.5 | 88.9% | estimated ± 7.4 pp, low confidence |