Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 E2B
~39
2/8 categoriesMoonshot v1
43
Winner · 2/8 categoriesGemma 4 E2B· Moonshot v1
Pick Moonshot v1 if you want the stronger benchmark profile. Gemma 4 E2B only becomes the better choice if coding is the priority or you want the stronger reasoning-first profile.
Moonshot v1 is clearly ahead on the aggregate, 43 to 39. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Moonshot v1's sharpest advantage is in reasoning, where it averages 54.9 against 19.1. The single biggest benchmark swing on the page is BBH, 21.9% to 73%. Gemma 4 E2B does hit back in coding, so the answer changes if that is the part of the workload you care about most.
Gemma 4 E2B 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 E2B | Moonshot v1 |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 39% |
| BrowseComp | — | 49% |
| OSWorld-Verified | — | 41% |
| CodingGemma 4 E2B wins | ||
| LiveCodeBench | 44% | 21% |
| HumanEval | — | 45% |
| SWE-bench Verified | — | 34% |
| SWE-bench Pro | — | 30% |
| Multimodal & GroundedMoonshot v1 wins | ||
| MMMU-Pro | 44.2% | 49% |
| OfficeQA Pro | — | 57% |
| ReasoningMoonshot v1 wins | ||
| BBH | 21.9% | 73% |
| MRCRv2 | 19.1% | 56% |
| MuSR | — | 49% |
| LongBench v2 | — | 58% |
| KnowledgeGemma 4 E2B wins | ||
| GPQA | 43.4% | 52% |
| MMLU-Pro | 60% | 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% |
Moonshot v1 is ahead overall, 43 to 39. The biggest single separator in this matchup is BBH, where the scores are 21.9% and 73%.
Gemma 4 E2B has the edge for knowledge tasks in this comparison, averaging 54.1 versus 42.9. 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 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 19.1. Inside this category, BBH is the benchmark that creates the most daylight between them.
Moonshot v1 has the edge for multimodal and grounded tasks in this comparison, averaging 52.6 versus 44.2. 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.