Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 31B
73
Winner · 2/8 categoriesGPT-4.1
64
2/8 categoriesGemma 4 31B· GPT-4.1
Pick Gemma 4 31B if you want the stronger benchmark profile. GPT-4.1 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 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 coding, where it averages 80 against 52.4. The single biggest benchmark swing on the page is GPQA, 84.3% to 66.3%. GPT-4.1 does hit back in reasoning, so the answer changes if that is the part of the workload you care about most.
GPT-4.1 is also the more expensive model on tokens at $2.00 input / $8.00 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 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 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 |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 61% |
| BrowseComp | — | 73% |
| OSWorld-Verified | — | 63% |
| CodingGemma 4 31B wins | ||
| LiveCodeBench | 80% | — |
| SWE-bench Verified | — | 54.6% |
| SWE-bench Pro | — | 51% |
| Multimodal & GroundedGemma 4 31B wins | ||
| MMMU-Pro | 76.9% | 70% |
| OfficeQA Pro | — | 78% |
| ReasoningGPT-4.1 wins | ||
| BBH | 74.4% | — |
| MRCRv2 | 66.4% | 82% |
| LongBench v2 | — | 80% |
| KnowledgeGPT-4.1 wins | ||
| GPQA | 84.3% | 66.3% |
| MMLU-Pro | 85.2% | — |
| HLE | 26.5% | — |
| HLE w/o tools | 19.5% | — |
| MMLU | — | 90.2% |
| FrontierScience | — | 61% |
| Instruction Following | ||
| IFEval | — | 87.4% |
| Multilingual | ||
| MMLU-ProX | — | 69% |
| Mathematics | ||
| AIME 2024 | — | 26.4% |
Gemma 4 31B is ahead overall, 73 to 64. The biggest single separator in this matchup is GPQA, where the scores are 84.3% and 66.3%.
GPT-4.1 has the edge for knowledge tasks in this comparison, averaging 63.1 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 52.4. GPT-4.1 stays close enough that the answer can still flip depending on your workload.
GPT-4.1 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 73.6. 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.