OpenBMB
availableShows if the model has enough results for an index.MiniCPM5-2B
MiniCPM5-2B is a reasoning model from OpenBMB in the MiniCPM5 family. 25 benchmarks count toward its score, in 6 categories.
IndexOverall score out of 100.37.3 ±4.7
CoverageShare of the index weight with results.85%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.131K
EloLMArena rating and rank.N/A
The index is a score out of 100. The ± range shows how much it can change.
CapabilitiesScore per category, out of 100.
Out of 100Results
25 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| MATH-500 Problem Set | Math | 94.6% | 47.5 | — | — | Dan Hendrycks et al. |
| Instruction-Following Eval | Instruction | 86.7% | 38.1 | — | — | Jeffrey Zhou et al. |
| American Invitational Mathematics Examination 2025 | Math | 86.5% | 45.0 | — | — | Mathematical Association of America |
| AIME 2026 | Math | 86.5% | 47.9 | — | — | Qwen |
| MMLU-Redux | Knowledge | 84.7% | 37.7 | — | — | Qwen |
| Massive Multitask Language Understanding Professional | Knowledge | 70.8% | 32.0 | — | — | Yubo Wang et al. |
| GPQA Diamond | Knowledge | 70.2% | 43.1 | — | — | David Rein et al. |
| Artificial Analysis GPQA Diamond | Knowledge | 70.2% | 40.5 | — | — | Artificial Analysis |
| LiveCodeBench v6 | Coding | 69.1% | 39.9 | — | — | LiveCodeBench maintainers |
| Berkeley Function Calling Leaderboard v4 | Agentic | 66.6% | 51.4 | — | — | Arcee AI |
| Instruction Following Benchmark | Instruction | 66.3% | 43.2 | — | — | Benchmark authors |
| Harvard-MIT Mathematics Tournament February 2026 | Math | 63.8% | 37.7 | — | — | Qwen |
| Artificial Analysis Long Context Reasoning | Reasoning | 59.0% | 49.1 | — | — | Artificial Analysis |
| Software Engineering Benchmark Verified | Coding | 46.4% | 34.7 | — | — | Carlos E. Jimenez et al. |
| LongBench v2 | Reasoning | 43.7% | — | — | — | LongBench v2 authors |
| SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines | Knowledge | 40.8% | 31.1 | — | — | Xiaoxuan Du et al. |
| Scientific Code Benchmark | Coding | 26.3% | 35.3 | — | — | Benchmark authors |
| Artificial Analysis SciCode | Coding | 26.3% | 29.4 | — | — | Artificial Analysis |
| SWE-bench Pro | Coding | 14.4% | 17.9 | — | — | Xiang Deng et al. |
| Artificial Analysis Intelligence Index | Knowledge | 12.5% | 38.0 | — | — | Artificial Analysis |
| GDPval-AA normalized | Agentic | 9.7% | 43.0 | — | — | Artificial Analysis |
| Humanity's Last Exam | Knowledge | 8.9% | 36.3 | — | — | Center for AI Safety et al. |
| Artificial Analysis Humanity's Last Exam | Knowledge | 8.9% | 34.2 | — | — | Artificial Analysis |
| Terminal-Bench 2.1 (provider run) | Agentic | 8.6% | 29.1 | — | — | DeepSeek-AI |
| Terminal-Bench 2.1 (provider run) | Agentic | 8.6% | 29.1 | — | — | DeepSeek-AI |
| Artificial Analysis Omniscience Accuracy | Knowledge | 8.4% | 24.3 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.3% | 39.0 | — | — | Artificial Analysis |
25 benchmarks count, from 26 of 27 results. A grey row does not count. Too few models took that benchmark.