Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 31B
73
Winner · 2/8 categoriesGPT-4.1 mini
57
2/8 categoriesGemma 4 31B· GPT-4.1 mini
Pick Gemma 4 31B if you want the stronger benchmark profile. GPT-4.1 mini only becomes the better choice if reasoning is the priority or you need the larger 1M context window.
Gemma 4 31B is clearly ahead on the aggregate, 73 to 57. 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 27.6. The single biggest benchmark swing on the page is GPQA, 84.3% to 64.2%. GPT-4.1 mini does hit back in reasoning, so the answer changes if that is the part of the workload you care about most.
GPT-4.1 mini is also the more expensive model on tokens at $0.40 input / $1.60 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 is the reasoning model in the pair, while GPT-4.1 mini is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-4.1 mini gives you the larger context window at 1M, compared with 256K for Gemma 4 31B.
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 | GPT-4.1 mini |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 54% |
| BrowseComp | — | 71% |
| OSWorld-Verified | — | 49% |
| CodingGemma 4 31B wins | ||
| LiveCodeBench | 80% | — |
| SWE-bench Verified | — | 23.6% |
| SWE-bench Pro | — | 30% |
| Multimodal & GroundedGemma 4 31B wins | ||
| MMMU-Pro | 76.9% | — |
| OfficeQA Pro | — | 74% |
| ReasoningGPT-4.1 mini wins | ||
| BBH | 74.4% | — |
| MRCRv2 | 66.4% | 82% |
| LongBench v2 | — | 80% |
| KnowledgeGPT-4.1 mini wins | ||
| GPQA | 84.3% | 64.2% |
| MMLU-Pro | 85.2% | — |
| HLE | 26.5% | — |
| HLE w/o tools | 19.5% | — |
| MMLU | — | 87.5% |
| Instruction Following | ||
| IFEval | — | 88.5% |
| Multilingual | ||
| MMLU-ProX | — | 72% |
| Mathematics | ||
| AIME 2024 | — | 23.1% |
Gemma 4 31B is ahead overall, 73 to 57. The biggest single separator in this matchup is GPQA, where the scores are 84.3% and 64.2%.
GPT-4.1 mini has the edge for knowledge tasks in this comparison, averaging 64.2 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 27.6. GPT-4.1 mini stays close enough that the answer can still flip depending on your workload.
GPT-4.1 mini has the edge for reasoning in this comparison, averaging 80.9 versus 66.4. Inside this category, MRCRv2 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 74. GPT-4.1 mini stays close enough that the answer can still flip depending on your workload.
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.