Other · model
MiniCPM5-2B benchmark scores
As of 2026-10-07, MiniCPM5-2B (Other) has measured scores on 26 benchmarks and estimated scores on 73 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 | 12.5% | measured |
| CritPt | 0.3% | measured |
| GDPval-AA | 10.5% | 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 | 8.4% | measured |
| SciCode | 26.3% | measured |
| Terminal-Bench 2.1 | 8.6% | measured |
| BrowseComp | 44.6% | estimated ± 10.1 pp, low confidence |
| HLE w/ tools | 37.0% | estimated ± 6.1 pp, low confidence |
| IFEval | 86.7% | measured |
| LongBench v2 | 43.7% | measured |
| τ²-bench results | 87.6% | estimated ± 14.1 pp, low confidence |
| AA Coding Index | 23.2% | estimated ± 5.1 pp, medium confidence |
| APEX-Agents | 10.3% | estimated ± 10.0 pp, low confidence |
| APEX-Agents-AA | 11.5% | estimated ± 9.1 pp, medium confidence |
| BioMysteryBench (human-difficult) | 14.0% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 63.2% | estimated ± 8.4 pp, medium confidence |
| SWE-bench Verified | 46.4% | measured |
| AutomationBench | 28.4% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 66.6% | measured |
| CyberGym | 25.8% | estimated ± 6.2 pp, low confidence |
| JobBench | 3.0% | estimated ± 8.6 pp, low confidence |
| SWE-bench Pro | 14.4% | measured |
| WideResearch | 57.4% | estimated ± 9.1 pp, low confidence |
| AA Agentic Index | 6.5% | estimated ± 2.8 pp, high confidence |
| MMLU-Pro | 70.8% | measured |
| FrontierMath v2 (Tiers 1-3) | 24.4% | estimated ± 8.4 pp, low confidence |
| GPQA | 70.2% | estimated ± 0.4 pp, high confidence |
| AA-IFBench | 38.2% | estimated ± 8.2 pp, medium confidence |
| Gert Labs | 38.3% | estimated ± 8.9 pp, medium confidence |
| AA-AnalystAgent | 6.8% | estimated ± 12.0 pp, low confidence |
| AA EnterpriseOps-Gym | 32.5% | estimated ± 6.7 pp, low confidence |
| ARC-AGI-1 | 47.2% | estimated ± 2.7 pp, medium confidence |
| ARC-AGI-2 | 19.1% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 0.0% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 0.0% | estimated ± 3.6 pp, medium confidence |
| Terminal-Bench 3.0 | 0.3% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 0.0% | estimated ± 2.7 pp, low confidence |
| FrontierSWE v2 | 0.0% | estimated ± 9.0 pp, low confidence |
| OSWorld-Verified | 61.1% | estimated ± 8.7 pp, low confidence |
| Vals GPQA Diamond | 68.9% | estimated ± 2.0 pp, medium confidence |
| Vals LiveCodeBench | 80.4% | estimated ± 0.8 pp, low confidence |
| Vals MMLU-Pro | 74.7% | estimated ± 1.6 pp, medium confidence |
| Vals SWE-bench | 19.4% | estimated ± 5.3 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 12.6% | estimated ± 7.4 pp, low confidence |
| AA AutomationBench | 3.7% | estimated ± 7.0 pp, low confidence |
| GDP.pdf | 9.4% | estimated ± 5.4 pp, low confidence |
| AA Tau3 Banking | 22.0% | estimated ± 5.8 pp, low confidence |
| AA Terminal-Bench 2.1 | 52.1% | estimated ± 3.5 pp, medium confidence |
| AA Terminal-Bench 4.0 | 0.0% | estimated ± 8.9 pp, low confidence |
| CursorBench 4.0 | 1.0% | estimated ± 3.5 pp, medium confidence |
| CWE-bench v1 | 17.2% | estimated ± 6.9 pp, low confidence |
| HLE w/o tools | 6.1% | estimated ± 4.4 pp, medium confidence |
| PostTrainBench v1.1 | 4.6% | estimated ± 4.7 pp, medium confidence |
| Toolathlon-Verified | 27.0% | estimated ± 2.4 pp, medium confidence |
| Vibe Code Bench | 0.6% | estimated ± 8.1 pp, low confidence |
| C-Eval | 76.4% | estimated ± 0.7 pp, low confidence |
| Claw-Eval | 64.0% | estimated ± 2.3 pp, medium confidence |
| HMMT Feb 2025 | 79.9% | estimated ± 1.8 pp, low confidence |
| HMMT Feb 2026 | 63.8% | measured |
| MCP Atlas | 56.5% | estimated ± 11.1 pp, low confidence |
| MMAnswerBench | 69.3% | estimated ± 1.3 pp, medium confidence |
| MMLU-Redux | 84.7% | measured |
| NL2Repo | 37.7% | estimated ± 3.1 pp, low confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| SuperGPQA | 40.8% | measured |
| Toolathlon | 26.9% | estimated ± 6.3 pp, low confidence |
| HealthBench Hard | 0.5% | estimated ± 7.7 pp, low confidence |
| LiveCodeBench Pro | 30.4% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (Text) | 22.5% | estimated ± 4.5 pp, low confidence |
| MMLU-Pro (Arcee) | 79.1% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 66.6% | estimated ± 4.7 pp, low confidence |
| ResearchClawBench | 11.2% | estimated ± 2.2 pp, low confidence |
| SWE-Rebench | 57.0% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| DRACO | 65.9% | estimated ± 3.0 pp, low confidence |
| FrontierCode 1.1 Extended | 26.4% | estimated ± 3.0 pp, low confidence |
| HealthBench (raw) | 13.5% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 16.7% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 27.0% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 50.9% | estimated ± 1.8 pp, low confidence |
| AIME 2025 | 86.5% | measured |
| LiveCodeBench | 61.3% | estimated ± 10.2 pp, low confidence |
| OpenHarmony Bench | 51.0% | estimated ± 2.4 pp, medium confidence |
| IMOAnswerBench | 67.5% | estimated ± 5.9 pp, medium confidence |
| MMMLU | 74.6% | estimated ± 1.1 pp, low confidence |
| MMLU | 71.1% | estimated ± 1.1 pp, low confidence |
| MATH-500 | 94.6% | measured |