MiniCPM5-1B
OpenBMBOpen weightsReasoningProvisionalReleased May 25, 2026
Overall score
6.2
Rank 222 of 222 · 0.0–20.6
Context window
131K
131,000 tokens
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Knowledge40.4
- 2Math12.1
- 3Instruction following#1429.7
Benchmark results (13)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Math
| AIME 2025 | 40.4 | #32 of 38 |
| AIME26 | 40.4 | #29 of 29 |
| HMMT Feb 2026 | 25.8 | #24 of 24 |
| MATH-500 | 91.6 | #13 of 20 |
Knowledge
| MMLU-Pro | 48.9 | #59 of 67 |
| SuperGPQA | 23.1 | #20 of 20 |
| MMLU-Redux | 70.1 | #15 of 15 |
Coding
| LiveCodeBench v6 | 33.5 | #45 of 46 |
| LiveCodeBench Pro | 22.7 | #6 of 6 |
Instruction following
| IFEval | 80.4 | #44 of 53 |
| IFBench | 46.7 | #39 of 42 |
Agentic & tool use
| BFCL v4 | 25.1 | #17 of 19 |
Reasoning
| BBH | 71.9 | #3 of 7 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price | — | — | — |
Speed
Measured by us through OpenRouter (median of trials).
Not available on OpenRouter, so we cannot measure it yet.
Related models
Similar score
- Mistral 7B v0.37.2 · —
- Nemotron-4 15B9.9 · —
- Gemini 1.0 Pro11.6 · —
- Claude 3 Haiku14.1 · $0.50
- Mixtral 8x22B Instruct v0.118.1 · —