Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 E4B
~47
Winner · 2/8 categoriesMoonshot v1
43
1/8 categoriesGemma 4 E4B· Moonshot v1
Pick Gemma 4 E4B if you want the stronger benchmark profile. Moonshot v1 only becomes the better choice if reasoning is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Gemma 4 E4B is clearly ahead on the aggregate, 47 to 43. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Gemma 4 E4B's sharpest advantage is in coding, where it averages 52 against 27.5. The single biggest benchmark swing on the page is BBH, 33.1% to 73%. Moonshot v1 does hit back in reasoning, 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 Moonshot v1 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 | Moonshot v1 |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 39% |
| BrowseComp | — | 49% |
| OSWorld-Verified | — | 41% |
| CodingGemma 4 E4B wins | ||
| LiveCodeBench | 52% | 21% |
| HumanEval | — | 45% |
| SWE-bench Verified | — | 34% |
| SWE-bench Pro | — | 30% |
| Multimodal & GroundedTie | ||
| MMMU-Pro | 52.6% | 49% |
| OfficeQA Pro | — | 57% |
| ReasoningMoonshot v1 wins | ||
| BBH | 33.1% | 73% |
| MRCRv2 | 25.4% | 56% |
| MuSR | — | 49% |
| LongBench v2 | — | 58% |
| KnowledgeGemma 4 E4B wins | ||
| GPQA | 58.6% | 52% |
| MMLU-Pro | 69.4% | 64% |
| MMLU | — | 53% |
| SuperGPQA | — | 50% |
| HLE | — | 5% |
| FrontierScience | — | 49% |
| SimpleQA | — | 51% |
| Instruction Following | ||
| IFEval | — | 77% |
| Multilingual | ||
| MGSM | — | 73% |
| MMLU-ProX | — | 68% |
| Mathematics | ||
| AIME 2023 | — | 53% |
| AIME 2024 | — | 55% |
| AIME 2025 | — | 54% |
| HMMT Feb 2023 | — | 49% |
| HMMT Feb 2024 | — | 51% |
| HMMT Feb 2025 | — | 50% |
| BRUMO 2025 | — | 52% |
| MATH-500 | — | 72% |
Gemma 4 E4B is ahead overall, 47 to 43. 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 42.9. 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 27.5. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.
Moonshot v1 has the edge for reasoning in this comparison, averaging 54.9 versus 25.4. Inside this category, BBH is the benchmark that creates the most daylight between them.
Gemma 4 E4B and Moonshot v1 are effectively tied for multimodal and grounded tasks here, both landing at 52.6 on average.
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.