Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 31B
73
Winner · 2/8 categoriesGrok 3 Mini
~49
0/8 categoriesGemma 4 31B· Grok 3 Mini
Pick Gemma 4 31B if you want the stronger benchmark profile. Grok 3 Mini only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Gemma 4 31B is clearly ahead on the aggregate, 73 to 49. 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 coding, where it averages 80 against 41.5. The single biggest benchmark swing on the page is LiveCodeBench, 80% to 41.5%.
Grok 3 Mini is also the more expensive model on tokens at $0.30 input / $0.50 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Gemma 4 31B. That is roughly Infinityx on output cost alone. Gemma 4 31B gives you the larger context window at 256K, compared with 128K for Grok 3 Mini.
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 | Grok 3 Mini |
|---|---|---|
| Agentic | ||
| Coming soon | ||
| CodingGemma 4 31B wins | ||
| LiveCodeBench | 80% | 41.5% |
| Multimodal & Grounded | ||
| MMMU-Pro | 76.9% | — |
| Reasoning | ||
| BBH | 74.4% | — |
| MRCRv2 | 66.4% | — |
| KnowledgeGemma 4 31B wins | ||
| GPQA | 84.3% | 66.2% |
| MMLU-Pro | 85.2% | 78.9% |
| HLE | 26.5% | — |
| HLE w/o tools | 19.5% | — |
| SimpleQA | — | 21.7% |
| Instruction Following | ||
| Coming soon | ||
| Multilingual | ||
| Coming soon | ||
| Mathematics | ||
| AIME 2024 | — | 95.8% |
Gemma 4 31B is ahead overall, 73 to 49. The biggest single separator in this matchup is LiveCodeBench, where the scores are 80% and 41.5%.
Gemma 4 31B has the edge for knowledge tasks in this comparison, averaging 61.3 versus 59.8. 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 41.5. Inside this category, LiveCodeBench 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.