Other · model
MiniCPM5-2B benchmark scores
As of 2026-11-22, MiniCPM5-2B (Other) has measured scores on 24 benchmarks and estimated scores on 70 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 70.2% | measured |
| AA-HLE | 8.9% | measured |
| AA-SciCode | 26.3% | measured |
| AIME26 | 86.5% | measured |
| Artificial Analysis Intelligence Index | 11.9% | estimated ± 3.0 pp, medium confidence |
| CritPt | 0.3% | measured |
| GDPval-AA | 10.4% | measured |
| GPQA Diamond | 70.2% | measured |
| HLE | 8.9% | measured |
| IFBench | 66.3% | measured |
| AA-LCR | 59.0% | measured |
| LiveCodeBench v6 | 69.1% | measured |
| AA-Omniscience Accuracy | 18.9% | estimated ± 6.7 pp, low confidence |
| SciCode | 26.3% | measured |
| Terminal-Bench 2.1 | 8.6% | measured |
| BrowseComp | 43.8% | estimated ± 9.2 pp, medium confidence |
| HLE w/ tools | 38.8% | estimated ± 5.3 pp, low confidence |
| IFEval | 86.7% | measured |
| LongBench v2 | 43.7% | measured |
| τ²-bench results | 88.0% | estimated ± 12.4 pp, low confidence |
| AA Coding Index | 24.0% | estimated ± 5.3 pp, medium confidence |
| APEX-Agents | 6.9% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 12.4% | estimated ± 9.5 pp, medium confidence |
| BioMysteryBench (human-difficult) | 6.5% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 63.3% | estimated ± 9.6 pp, medium confidence |
| SWE-bench Verified | 46.4% | measured |
| BFCL v4 | 66.6% | measured |
| CyberGym | 25.9% | estimated ± 6.0 pp, low confidence |
| JobBench | 4.0% | estimated ± 8.7 pp, low confidence |
| SWE-bench Pro | 14.4% | measured |
| WideResearch | 57.2% | estimated ± 7.8 pp, low confidence |
| AA Agentic Index | 7.4% | estimated ± 3.1 pp, high confidence |
| MMLU-Pro | 70.8% | measured |
| AA-IFBench | 56.7% | estimated ± 7.4 pp, medium confidence |
| AIME 2024 | 90.0% | estimated ± 2.6 pp, high confidence |
| BBH | 90.2% | estimated ± 2.8 pp, medium confidence |
| GPQA | 70.0% | estimated ± 1.2 pp, high confidence |
| MMLU | 84.6% | estimated ± 2.1 pp, high confidence |
| Vals GPQA Diamond | 69.3% | estimated ± 3.2 pp, high confidence |
| Vals LiveCodeBench | 0.3% | estimated ± 4.7 pp, low confidence |
| Vals MMLU-Pro | 81.0% | estimated ± 2.4 pp, low confidence |
| MATH-500 | 94.6% | measured |
| MMMLU | 85.4% | estimated ± 0.7 pp, medium confidence |
| AIME 2025 | 86.5% | measured |
| AA MMLU-Pro | 85.7% | estimated ± 1.3 pp, medium confidence |
| Gert Labs | 27.7% | estimated ± 10.0 pp, low confidence |
| AA Tau3 Banking | 16.1% | estimated ± 4.1 pp, medium confidence |
| ARC-AGI-1 | 75.0% | estimated ± 7.8 pp, low confidence |
| ARC-AGI-2 | 31.1% | estimated ± 14.4 pp, low confidence |
| FrontierMath v2 (Tiers 1-3) | 0.0% | estimated ± 8.8 pp, low confidence |
| FrontierSWE v2 | 0.5% | estimated ± 14.2 pp, low confidence |
| MazeBench | 0.4% | estimated ± 5.5 pp, low confidence |
| OSWorld-Verified | 60.9% | estimated ± 8.4 pp, low confidence |
| Vals SWE-bench | 31.0% | estimated ± 6.6 pp, low confidence |
| CWE-Bench-AA | 15.5% | estimated ± 10.1 pp, low confidence |
| DeepsecBench-AA | 0.0% | estimated ± 8.9 pp, low confidence |
| AA ITBench | 35.7% | estimated ± 5.1 pp, low confidence |
| Bug Hunt Bench | 7.7% | estimated ± 10.5 pp, low confidence |
| CWE-bench v1 | 16.6% | estimated ± 6.4 pp, low confidence |
| DeepSWE | 4.0% | estimated ± 7.5 pp, low confidence |
| DRACO | 52.3% | estimated ± 2.0 pp, low confidence |
| HLE w/o tools | 9.3% | estimated ± 4.3 pp, medium confidence |
| Toolathlon-Verified | 28.4% | estimated ± 3.1 pp, medium confidence |
| GDP.pdf | 17.0% | estimated ± 4.6 pp, medium confidence |
| ARC-AGI-3 | 1.3% | estimated ± 9.8 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| Vibe Code Bench | 0.0% | estimated ± 8.4 pp, low confidence |
| Hermes Bench | 35.4% | estimated ± 2.9 pp, medium confidence |
| Hermes Index | 10.2% | estimated ± 8.7 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 10.6 pp, low confidence |
| C-Eval | 91.1% | estimated ± 1.1 pp, medium confidence |
| HMMT Feb 2025 | 77.3% | estimated ± 2.9 pp, high confidence |
| HMMT Feb 2026 | 63.8% | measured |
| HMMT Nov 2025 | 66.5% | estimated ± 2.8 pp, medium confidence |
| MCP Atlas | 56.6% | estimated ± 10.7 pp, low confidence |
| MMAnswerBench | 69.3% | estimated ± 1.3 pp, medium confidence |
| MMLU-Redux | 84.7% | measured |
| NL2Repo | 17.4% | estimated ± 3.4 pp, medium confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| SuperGPQA | 40.8% | measured |
| Toolathlon | 27.0% | estimated ± 6.3 pp, low confidence |
| HealthBench Hard | 3.5% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 79.1% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 64.5% | estimated ± 2.7 pp, low confidence |
| ResearchClawBench | 13.1% | estimated ± 2.2 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| ScarfBench | 22.2% | estimated ± 14.0 pp, low confidence |
| SimpleQA | 23.6% | estimated ± 7.8 pp, medium confidence |
| LiveCodeBench | 55.2% | estimated ± 14.6 pp, low confidence |
| IMOAnswerBench | 67.1% | estimated ± 5.6 pp, medium confidence |
| MRCRv2 | 25.7% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 60.2% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 33.9% | estimated ± 10.7 pp, low confidence |
| PinchBench | 89.1% | estimated ± 5.0 pp, low confidence |