Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 31B
73
Winner · 2/8 categorieso1-preview
72
2/8 categoriesGemma 4 31B· o1-preview
Pick Gemma 4 31B if you want the stronger benchmark profile. o1-preview only becomes the better choice if reasoning is the priority.
Gemma 4 31B finishes one point ahead overall, 73 to 72. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
Gemma 4 31B's sharpest advantage is in coding, where it averages 80 against 64.6. The single biggest benchmark swing on the page is LiveCodeBench, 80% to 60%. o1-preview does hit back in reasoning, so the answer changes if that is the part of the workload you care about most.
Gemma 4 31B gives you the larger context window at 256K, compared with 200K for o1-preview.
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 | o1-preview |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 77% |
| BrowseComp | — | 79% |
| OSWorld-Verified | — | 71% |
| CodingGemma 4 31B wins | ||
| LiveCodeBench | 80% | 60% |
| HumanEval | — | 86% |
| SWE-bench Verified | — | 65% |
| SWE-bench Pro | — | 69% |
| Multimodal & GroundedGemma 4 31B wins | ||
| MMMU-Pro | 76.9% | 72% |
| OfficeQA Pro | — | 80% |
| Reasoningo1-preview wins | ||
| BBH | 74.4% | 93% |
| MRCRv2 | 66.4% | 83% |
| MuSR | — | 86% |
| LongBench v2 | — | 87% |
| Knowledgeo1-preview wins | ||
| GPQA | 84.3% | 90% |
| MMLU-Pro | 85.2% | 80% |
| HLE | 26.5% | 32% |
| HLE w/o tools | 19.5% | — |
| MMLU | — | 92% |
| SuperGPQA | — | 88% |
| FrontierScience | — | 83% |
| SimpleQA | — | 88% |
| Instruction Following | ||
| IFEval | — | 88% |
| Multilingual | ||
| MGSM | — | 90% |
| MMLU-ProX | — | 86% |
| Mathematics | ||
| AIME 2023 | — | 94% |
| AIME 2024 | — | 96% |
| AIME 2025 | — | 95% |
| HMMT Feb 2023 | — | 90% |
| HMMT Feb 2024 | — | 92% |
| HMMT Feb 2025 | — | 91% |
| BRUMO 2025 | — | 93% |
| MATH-500 | — | 94% |
Gemma 4 31B is ahead overall, 73 to 72. The biggest single separator in this matchup is LiveCodeBench, where the scores are 80% and 60%.
o1-preview has the edge for knowledge tasks in this comparison, averaging 72.7 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 64.6. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
o1-preview has the edge for reasoning in this comparison, averaging 85.4 versus 66.4. Inside this category, BBH 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 75.6. 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.