Other · model
ZAYA1-8B benchmark scores
As of 2026-11-22, ZAYA1-8B (Other) has measured scores on 10 benchmarks and estimated scores on 34 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 68.6% | estimated ± 4.4 pp, high confidence |
| AA-HLE | 10.1% | estimated ± 3.9 pp, high confidence |
| AA-SciCode | 27.0% | estimated ± 4.7 pp, high confidence |
| AIME26 | 89.1% | measured |
| Artificial Analysis Intelligence Index | 10.1% | estimated ± 7.4 pp, medium confidence |
| CritPt | 0.3% | estimated ± 4.0 pp, high confidence |
| GDPval-AA | 0.0% | estimated ± 5.5 pp, low confidence |
| GPQA Diamond | 71.0% | measured |
| HLE | 9.6% | estimated ± 6.5 pp, medium confidence |
| IFBench | 52.6% | measured |
| LiveCodeBench v6 | 65.8% | measured |
| AA-Omniscience Accuracy | 10.6% | estimated ± 8.4 pp, medium confidence |
| SciCode | 26.5% | estimated ± 4.9 pp, high confidence |
| IFEval | 85.6% | measured |
| τ²-bench results | 63.2% | estimated ± 12.4 pp, low confidence |
| AA Coding Index | 18.3% | estimated ± 5.7 pp, medium confidence |
| SWE-bench Verified | 57.5% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 39.2% | measured |
| SWE-bench Pro | 9.4% | estimated ± 6.0 pp, low confidence |
| MMLU-Pro | 74.2% | measured |
| AA-IFBench | 56.7% | estimated ± 7.4 pp, medium confidence |
| BBH | 92.4% | estimated ± 2.8 pp, medium confidence |
| GPQA | 71.0% | measured |
| MMLU | 86.1% | estimated ± 2.1 pp, high confidence |
| Vals GPQA Diamond | 68.9% | estimated ± 4.5 pp, high confidence |
| Vals MMLU-Pro | 79.4% | estimated ± 2.3 pp, high confidence |
| MATH-500 | 96.8% | estimated ± 3.1 pp, medium confidence |
| MMMLU | 75.7% | estimated ± 1.1 pp, low confidence |
| AIME 2025 | 89.9% | estimated ± 1.8 pp, medium confidence |
| AA MMLU-Pro | 85.3% | estimated ± 1.2 pp, low confidence |
| ARC-AGI-1 | 23.1% | estimated ± 6.7 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 10.9 pp, low confidence |
| FrontierMath v2 (Tiers 1-3) | 5.9% | estimated ± 8.8 pp, low confidence |
| HLE w/o tools | 9.4% | estimated ± 4.3 pp, medium confidence |
| C-Eval | 88.8% | estimated ± 1.2 pp, high confidence |
| HMMT Feb 2026 | 71.6% | measured |
| HMMT Nov 2025 | 80.1% | estimated ± 2.8 pp, medium confidence |
| MMAnswerBench | 73.2% | estimated ± 1.3 pp, medium confidence |
| MMLU-Redux | 86.9% | estimated ± 0.6 pp, high confidence |
| SuperGPQA | 50.4% | estimated ± 8.5 pp, low confidence |
| MMLU-Pro (Arcee) | 79.4% | estimated ± 3.4 pp, medium confidence |
| SimpleQA | 23.7% | estimated ± 11.7 pp, low confidence |
| IMOAnswerBench | 59.3% | measured |
| PinchBench | 43.5% | estimated ± 5.0 pp, low confidence |