# Gemma 4 31B vs MiniCPM5-2B

> Side-by-side benchmark comparison for Gemma 4 31B and MiniCPM5-2B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gemma-4-31b-vs-minicpm5-2b
- Last updated: September 10, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: Gemma 4 31B and MiniCPM5-2B share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Gemma 4 31B has the larger published context window at 256K.

## Model Snapshot

| Property | Gemma 4 31B | MiniCPM5-2B |
|----------|----------|----------|
| Creator | Google | OpenBMB |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 131K |
| Independent public score (not head-to-head) | 52.56 | null |
| Benchmarks Covered | 8 | 19 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 45.5 (Estimated · #81/152)
- MiniCPM5-2B public-lane score: Coming soon

| Benchmark | Gemma 4 31B | MiniCPM5-2B | Winner |
|-----------|-----------|-----------|--------|
| Gert Labs | 35.26% | Coming soon | Coming soon |
| BFCL v4 | Coming soon | 66.6% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 8.6% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 42.4 (Supported · #105/151)
- MiniCPM5-2B public-lane score: Coming soon

| Benchmark | Gemma 4 31B | MiniCPM5-2B | Winner |
|-----------|-----------|-----------|--------|
| SWE-Rebench | 41.6% | Coming soon | Coming soon |
| React Native Evals | 75.2% | Coming soon | Coming soon |
| LiveCodeBench v6 | Coming soon | 69.1% | Coming soon |
| SciCode | Coming soon | 26.3% | Coming soon |
| SWE-bench Verified | Coming soon | 46.4% | Coming soon |
| SWE-bench Pro | Coming soon | 14.4% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 8.6% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 58.4 (#30/48)
- MiniCPM5-2B public-lane score: Coming soon

| Benchmark | Gemma 4 31B | MiniCPM5-2B | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 76.9% | Coming soon | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 68.9 (Unranked · 2 rankable rows)
- MiniCPM5-2B public-lane score: Coming soon

| Benchmark | Gemma 4 31B | MiniCPM5-2B | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | Coming soon | 43.7% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 45.8 (Supported · #104/183)
- MiniCPM5-2B public-lane score: Coming soon

| Benchmark | Gemma 4 31B | MiniCPM5-2B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 84.3% | Coming soon | Coming soon |
| MMLU-Pro | 85.2% | 70.8% | Gemma 4 31B |
| HLE | 26.5% | 8.9% | Gemma 4 31B |
| HLE w/o tools | 19.5% | Coming soon | Coming soon |
| MMLU-Redux | Coming soon | 84.7% | Coming soon |
| GPQA-D | Coming soon | 70.2% | Coming soon |
| SuperGPQA | Coming soon | 40.8% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 92.8 (#12/123)
- MiniCPM5-2B public-lane score: Coming soon

| Benchmark | Gemma 4 31B | MiniCPM5-2B | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 66.3% | Coming soon |
| IFEval | Coming soon | 86.7% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: Coming soon
- MiniCPM5-2B public-lane score: Coming soon

| Benchmark | Gemma 4 31B | MiniCPM5-2B | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | Coming soon | 86.5% | Coming soon |
| AIME26 | Coming soon | 86.5% | Coming soon |
| HMMT Feb 2026 | Coming soon | 63.8% | Coming soon |
| MATH-500 | Coming soon | 94.6% | Coming soon |

## FAQ

### Is there enough evidence to pick between Gemma 4 31B and MiniCPM5-2B?

Not yet. The models share only 2 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Gemma 4 31B vs Gemma 4 26B A4B](/compare/gemma-4-26b-a4b-vs-gemma-4-31b)
- [MiniCPM5-2B vs Gemma 4 26B A4B](/compare/gemma-4-26b-a4b-vs-minicpm5-2b)
- [Gemma 4 31B vs Gemma 4 12B](/compare/gemma-4-12b-vs-gemma-4-31b)
- [MiniCPM5-2B vs Gemma 4 12B](/compare/gemma-4-12b-vs-minicpm5-2b)

## Explore More

- [Gemma 4 31B profile](/models/gemma-4-31b)
- [MiniCPM5-2B profile](/models/minicpm5-2b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)