Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 E4B
~47
3/8 categoriesGPT-OSS 120B
50
Winner · 1/8 categoriesGemma 4 E4B· GPT-OSS 120B
Pick GPT-OSS 120B if you want the stronger benchmark profile. Gemma 4 E4B only becomes the better choice if coding is the priority or you want the stronger reasoning-first profile.
GPT-OSS 120B has the cleaner overall profile here, landing at 50 versus 47. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
GPT-OSS 120B's sharpest advantage is in reasoning, where it averages 55.4 against 25.4. The single biggest benchmark swing on the page is BBH, 33.1% to 73%. Gemma 4 E4B does hit back in coding, so the answer changes if that is the part of the workload you care about most.
Gemma 4 E4B is the reasoning model in the pair, while GPT-OSS 120B 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 | GPT-OSS 120B |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 43% |
| BrowseComp | — | 50% |
| OSWorld-Verified | — | 43% |
| CodingGemma 4 E4B wins | ||
| LiveCodeBench | 52% | 25% |
| HumanEval | — | 43% |
| SWE-bench Verified | — | 29% |
| SWE-bench Pro | — | 31% |
| SWE-Rebench | — | 33.3% |
| React Native Evals | — | 66.4% |
| Multimodal & GroundedGemma 4 E4B wins | ||
| MMMU-Pro | 52.6% | 42% |
| OfficeQA Pro | — | 57% |
| ReasoningGPT-OSS 120B wins | ||
| BBH | 33.1% | 73% |
| MRCRv2 | 25.4% | 59% |
| MuSR | — | 47% |
| LongBench v2 | — | 58% |
| KnowledgeGemma 4 E4B wins | ||
| GPQA | 58.6% | 80.9% |
| MMLU-Pro | 69.4% | 90% |
| MMLU | — | 90% |
| SuperGPQA | — | 48% |
| HLE | — | 5% |
| FrontierScience | — | 49% |
| SimpleQA | — | 49% |
| Instruction Following | ||
| IFEval | — | 79% |
| Multilingual | ||
| MGSM | — | 72% |
| MMLU-ProX | — | 70% |
| Mathematics | ||
| AIME 2023 | — | 51% |
| AIME 2024 | — | 53% |
| AIME 2025 | — | 52% |
| HMMT Feb 2023 | — | 47% |
| HMMT Feb 2024 | — | 49% |
| HMMT Feb 2025 | — | 48% |
| BRUMO 2025 | — | 50% |
| MATH-500 | — | 71% |
GPT-OSS 120B is ahead overall, 50 to 47. The biggest single separator in this matchup is BBH, where the scores are 33.1% and 73%.
Gemma 4 E4B has the edge for knowledge tasks in this comparison, averaging 65.6 versus 51.6. 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. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
GPT-OSS 120B has the edge for reasoning in this comparison, averaging 55.4 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 48.8. 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.