Other · model
Particle-1 benchmark scores
As of 2026-10-29, Particle-1 (Other) has measured scores on 4 benchmarks and estimated scores on 35 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 89.9% | estimated ± 4.4 pp, high confidence |
| AA-HLE | 36.0% | estimated ± 3.8 pp, high confidence |
| AA-SciCode | 58.2% | estimated ± 3.5 pp, medium confidence |
| CritPt | 12.7% | estimated ± 4.6 pp, high confidence |
| GPQA Diamond | 90.4% | measured |
| HLE | 40.0% | estimated ± 7.3 pp, medium confidence |
| Terminal-Bench 2.1 | 79.9% | measured |
| AA Coding Index | 77.0% | estimated ± 2.5 pp, high confidence |
| SWE-bench Verified | 92.3% | estimated ± 4.6 pp, high confidence |
| SWE-bench Pro | 75.3% | estimated ± 7.5 pp, low confidence |
| MMLU-Pro | 74.4% | estimated ± 4.0 pp, high confidence |
| Artificial Analysis Intelligence Index | 10.7% | estimated ± 2.1 pp, high confidence |
| BBH | 91.1% | estimated ± 2.4 pp, low confidence |
| GPQA | 90.3% | estimated ± 1.2 pp, high confidence |
| MMLU | 86.1% | measured |
| AA-Omniscience Accuracy | 18.1% | estimated ± 1.5 pp, high confidence |
| MMMLU | 90.0% | estimated ± 1.1 pp, medium confidence |
| AA Terminal-Bench 2.1 | 80.6% | estimated ± 6.8 pp, medium confidence |
| ARC-AGI-1 | 89.6% | estimated ± 2.7 pp, high confidence |
| ARC-AGI-2 | 57.5% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.2 | 67.9% | estimated ± 6.4 pp, low confidence |
| Terminal-Bench 3.0 | 13.3% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 51.7% | estimated ± 3.7 pp, low confidence |
| Vals GPQA Diamond | 89.7% | estimated ± 2.0 pp, high confidence |
| Vals MMLU-Pro | 86.8% | estimated ± 1.6 pp, high confidence |
| Terminal-Bench 2.1 (Vals AI) | 67.7% | estimated ± 7.4 pp, medium confidence |
| AA Terminal-Bench 4.0 | 17.8% | estimated ± 11.6 pp, low confidence |
| Bug Hunt Bench | 33.7% | estimated ± 9.4 pp, low confidence |
| DeepSWE | 72.6% | measured |
| HLE w/o tools | 36.4% | estimated ± 4.3 pp, high confidence |
| PostTrainBench v1.1 | 40.6% | estimated ± 4.5 pp, high confidence |
| ARC-AGI-3 | 0.0% | estimated ± 3.6 pp, high confidence |
| MMLU-Redux | 92.7% | estimated ± 2.8 pp, high confidence |
| NL2Repo | 61.1% | estimated ± 6.2 pp, medium confidence |
| SuperGPQA | 77.0% | estimated ± 13.9 pp, low confidence |
| MedXpertQA (Text) | 55.0% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 87.0% | estimated ± 3.4 pp, low confidence |
| HealthBench Professional | 50.9% | estimated ± 4.8 pp, low confidence |
| SWE-Atlas Codebase QnA | 63.5% | estimated ± 5.4 pp, low confidence |