Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 E4B
~47
3/8 categoriesQwen3 235B 2507
47
1/8 categoriesGemma 4 E4B· Qwen3 235B 2507
Treat this as a split decision. Gemma 4 E4B makes more sense if coding is the priority or you want the stronger reasoning-first profile; Qwen3 235B 2507 is the better fit if reasoning is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Gemma 4 E4B and Qwen3 235B 2507 finish on the same overall score, so this is less about a single winner and more about where the edge shows up. The headline says tie; the benchmark table is where the real choice happens.
Gemma 4 E4B is the reasoning model in the pair, while Qwen3 235B 2507 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.
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 E4B | Qwen3 235B 2507 |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 33% |
| BrowseComp | — | 40% |
| OSWorld-Verified | — | 30% |
| CodingGemma 4 E4B wins | ||
| LiveCodeBench | 52% | 51.8% |
| HumanEval | — | 31% |
| SWE-bench Verified | — | 15% |
| SWE-bench Pro | — | 19% |
| Multimodal & GroundedGemma 4 E4B wins | ||
| MMMU-Pro | 52.6% | 38% |
| OfficeQA Pro | — | 46% |
| ReasoningQwen3 235B 2507 wins | ||
| BBH | 33.1% | 60% |
| MRCRv2 | 25.4% | 52% |
| MuSR | — | 35% |
| LongBench v2 | — | 52% |
| KnowledgeGemma 4 E4B wins | ||
| GPQA | 58.6% | 77.5% |
| MMLU-Pro | 69.4% | 83% |
| MMLU | — | 39% |
| SuperGPQA | — | 62.6% |
| HLE | — | 1% |
| FrontierScience | — | 39% |
| SimpleQA | — | 54.3% |
| Instruction Following | ||
| IFEval | — | 88.7% |
| Multilingual | ||
| MGSM | — | 63% |
| MMLU-ProX | — | 79.4% |
| Mathematics | ||
| AIME 2023 | — | 39% |
| AIME 2024 | — | 41% |
| AIME 2025 | — | 70.3% |
| HMMT Feb 2023 | — | 35% |
| HMMT Feb 2024 | — | 37% |
| HMMT Feb 2025 | — | 36% |
| BRUMO 2025 | — | 38% |
| MATH-500 | — | 57% |
Gemma 4 E4B and Qwen3 235B 2507 are tied on overall score, so the right pick depends on which category matters most for your use case.
Gemma 4 E4B has the edge for knowledge tasks in this comparison, averaging 65.6 versus 49.4. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Gemma 4 E4B has the edge for coding in this comparison, averaging 52 versus 30.7. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Qwen3 235B 2507 has the edge for reasoning in this comparison, averaging 47.5 versus 25.4. Inside this category, BBH is the benchmark that creates the most daylight between them.
Gemma 4 E4B has the edge for multimodal and grounded tasks in this comparison, averaging 52.6 versus 41.6. 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.