Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 31B
73
Winner · 2/8 categoriesMistral Small 4 (Reasoning)
~64
1/8 categoriesGemma 4 31B· Mistral Small 4 (Reasoning)
Pick Gemma 4 31B if you want the stronger benchmark profile. Mistral Small 4 (Reasoning) only becomes the better choice if knowledge is the priority.
Gemma 4 31B is clearly ahead on the aggregate, 73 to 64. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Gemma 4 31B's sharpest advantage is in multimodal & grounded, where it averages 76.9 against 60. The single biggest benchmark swing on the page is MMMU-Pro, 76.9% to 60%. Mistral Small 4 (Reasoning) does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.
Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.
| Benchmark | Gemma 4 31B | Mistral Small 4 (Reasoning) |
|---|---|---|
| Agentic | ||
| Coming soon | ||
| CodingGemma 4 31B wins | ||
| LiveCodeBench | 80% | 63.6% |
| Multimodal & GroundedGemma 4 31B wins | ||
| MMMU-Pro | 76.9% | 60% |
| Reasoning | ||
| BBH | 74.4% | — |
| MRCRv2 | 66.4% | — |
| KnowledgeMistral Small 4 (Reasoning) wins | ||
| GPQA | 84.3% | 71.2% |
| MMLU-Pro | 85.2% | 78% |
| HLE | 26.5% | — |
| HLE w/o tools | 19.5% | — |
| Instruction Following | ||
| Coming soon | ||
| Multilingual | ||
| Coming soon | ||
| Mathematics | ||
| AIME 2025 | — | 83.8% |
Gemma 4 31B is ahead overall, 73 to 64. The biggest single separator in this matchup is MMMU-Pro, where the scores are 76.9% and 60%.
Mistral Small 4 (Reasoning) has the edge for knowledge tasks in this comparison, averaging 75.6 versus 61.3. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Gemma 4 31B has the edge for coding in this comparison, averaging 80 versus 63.6. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Gemma 4 31B has the edge for multimodal and grounded tasks in this comparison, averaging 76.9 versus 60. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.