Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 31B
73
Winner · 3/8 categoriesQwen3.5-35B-A3B
66
1/8 categoriesGemma 4 31B· Qwen3.5-35B-A3B
Pick Gemma 4 31B if you want the stronger benchmark profile. Qwen3.5-35B-A3B only becomes the better choice if knowledge is the priority or you need the larger 262K context window.
Gemma 4 31B is clearly ahead on the aggregate, 73 to 66. 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 72.6. The single biggest benchmark swing on the page is LiveCodeBench, 80% to 74.6%. Qwen3.5-35B-A3B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
Qwen3.5-35B-A3B gives you the larger context window at 262K, 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 | Qwen3.5-35B-A3B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 40.5% |
| BrowseComp | — | 61% |
| OSWorld-Verified | — | 54.5% |
| Tau2-Telecom | — | 81.2% |
| CodingGemma 4 31B wins | ||
| LiveCodeBench | 80% | 74.6% |
| SWE-bench Verified | — | 69.2% |
| Multimodal & GroundedGemma 4 31B wins | ||
| MMMU-Pro | 76.9% | 75.1% |
| ReasoningGemma 4 31B wins | ||
| BBH | 74.4% | — |
| MRCRv2 | 66.4% | — |
| LongBench v2 | — | 59% |
| KnowledgeQwen3.5-35B-A3B wins | ||
| GPQA | 84.3% | 84.2% |
| MMLU-Pro | 85.2% | 85.3% |
| HLE | 26.5% | — |
| HLE w/o tools | 19.5% | — |
| SuperGPQA | — | 63.4% |
| Instruction Following | ||
| IFEval | — | 91.9% |
| Multilingual | ||
| MMLU-ProX | — | 81% |
| Mathematics | ||
| Coming soon | ||
Gemma 4 31B is ahead overall, 73 to 66. The biggest single separator in this matchup is LiveCodeBench, where the scores are 80% and 74.6%.
Qwen3.5-35B-A3B has the edge for knowledge tasks in this comparison, averaging 79.3 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 72.6. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Gemma 4 31B has the edge for reasoning in this comparison, averaging 66.4 versus 59. Qwen3.5-35B-A3B stays close enough that the answer can still flip depending on your workload.
Gemma 4 31B has the edge for multimodal and grounded tasks in this comparison, averaging 76.9 versus 75.1. 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.