Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 E2B
~39
3/8 categoriesQwen3 235B 2507 (Reasoning)
55
Winner · 1/8 categoriesGemma 4 E2B· Qwen3 235B 2507 (Reasoning)
Pick Qwen3 235B 2507 (Reasoning) if you want the stronger benchmark profile. Gemma 4 E2B only becomes the better choice if knowledge is the priority.
Qwen3 235B 2507 (Reasoning) is clearly ahead on the aggregate, 55 to 39. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3 235B 2507 (Reasoning)'s sharpest advantage is in reasoning, where it averages 52.1 against 19.1. The single biggest benchmark swing on the page is BBH, 21.9% to 63%. Gemma 4 E2B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
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 E2B | Qwen3 235B 2507 (Reasoning) |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 47% |
| BrowseComp | — | 48% |
| CodingGemma 4 E2B wins | ||
| LiveCodeBench | 44% | 74.1% |
| HumanEval | — | 32% |
| SWE-bench Verified | — | 16% |
| SWE-bench Pro | — | 29% |
| Multimodal & GroundedGemma 4 E2B wins | ||
| MMMU-Pro | 44.2% | 38% |
| OfficeQA Pro | — | 47% |
| ReasoningQwen3 235B 2507 (Reasoning) wins | ||
| BBH | 21.9% | 63% |
| MRCRv2 | 19.1% | 58% |
| MuSR | — | 36% |
| LongBench v2 | — | 58% |
| KnowledgeGemma 4 E2B wins | ||
| GPQA | 43.4% | 81.1% |
| MMLU-Pro | 60% | 84.4% |
| MMLU | — | 40% |
| SuperGPQA | — | 64.9% |
| HLE | — | 6% |
| FrontierScience | — | 42% |
| SimpleQA | — | 38% |
| Instruction Following | ||
| IFEval | — | 87.8% |
| Multilingual | ||
| MGSM | — | 62% |
| MMLU-ProX | — | 81% |
| Mathematics | ||
| AIME 2023 | — | 40% |
| AIME 2024 | — | 42% |
| AIME 2025 | — | 92.3% |
| HMMT Feb 2023 | — | 36% |
| HMMT Feb 2024 | — | 38% |
| HMMT Feb 2025 | — | 37% |
| BRUMO 2025 | — | 39% |
| MATH-500 | — | 60% |
Qwen3 235B 2507 (Reasoning) is ahead overall, 55 to 39. The biggest single separator in this matchup is BBH, where the scores are 21.9% and 63%.
Gemma 4 E2B has the edge for knowledge tasks in this comparison, averaging 54.1 versus 50. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Gemma 4 E2B has the edge for coding in this comparison, averaging 44 versus 43.3. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Qwen3 235B 2507 (Reasoning) has the edge for reasoning in this comparison, averaging 52.1 versus 19.1. Inside this category, BBH is the benchmark that creates the most daylight between them.
Gemma 4 E2B has the edge for multimodal and grounded tasks in this comparison, averaging 44.2 versus 42.1. 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.