Other · model
Ministral 3 14B (Reasoning) benchmark scores
As of 2026-10-10, Ministral 3 14B (Reasoning) (Other) has measured scores on 3 benchmarks and estimated scores on 26 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 70.1% | estimated ± 4.7 pp, high confidence |
| AA-HLE | 8.6% | estimated ± 5.3 pp, medium confidence |
| AIME26 | 85.2% | estimated ± 4.6 pp, medium confidence |
| Artificial Analysis Intelligence Index | 10.1% | estimated ± 6.3 pp, medium confidence |
| CritPt | 0.6% | estimated ± 3.8 pp, high confidence |
| GPQA Diamond | 71.2% | estimated ± 0.4 pp, high confidence |
| HLE | 9.5% | estimated ± 6.4 pp, low confidence |
| AA-Omniscience Accuracy | 16.4% | estimated ± 8.6 pp, medium confidence |
| MMLU-Pro | 80.5% | estimated ± 4.0 pp, high confidence |
| FrontierMath v2 (Tier 4) | 1.0% | estimated ± 6.6 pp, low confidence |
| GPQA | 71.2% | measured |
| AIME 2025 | 85.0% | measured |
| ARC-AGI-1 | 17.8% | estimated ± 6.9 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 11.6 pp, low confidence |
| Vals GPQA Diamond | 57.4% | estimated ± 4.8 pp, medium confidence |
| Vals MMLU-Pro | 29.1% | estimated ± 1.2 pp, medium confidence |
| HLE w/o tools | 6.9% | estimated ± 4.9 pp, medium confidence |
| C-Eval | 0.0% | estimated ± 1.4 pp, low confidence |
| HMMT Feb 2025 | 80.1% | estimated ± 3.1 pp, high confidence |
| MMLU-Redux | 90.2% | estimated ± 1.9 pp, high confidence |
| SuperGPQA | 51.2% | estimated ± 8.2 pp, low confidence |
| HealthBench Hard | 0.0% | estimated ± 5.1 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| HealthBench Professional | 18.0% | estimated ± 4.8 pp, low confidence |
| AIME 2024 | 89.8% | measured |
| MATH-500 | 97.5% | estimated ± 2.9 pp, high confidence |
| MMLU | 88.2% | estimated ± 4.3 pp, high confidence |
| SimpleQA | 34.9% | estimated ± 10.9 pp, low confidence |
| BBH | 78.7% | estimated ± 10.9 pp, low confidence |