Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Gemma 4 E2B
~39
1/8 categoriesMistral Medium 3
~53
Winner · 1/8 categoriesGemma 4 E2B· Mistral Medium 3
Pick Mistral Medium 3 if you want the stronger benchmark profile. Gemma 4 E2B only becomes the better choice if coding is the priority or you want the cheaper token bill.
Mistral Medium 3 is clearly ahead on the aggregate, 53 to 39. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Mistral Medium 3's sharpest advantage is in knowledge, where it averages 70.1 against 54.1. The single biggest benchmark swing on the page is MMLU-Pro, 60% to 77.2%. Gemma 4 E2B does hit back in coding, so the answer changes if that is the part of the workload you care about most.
Mistral Medium 3 is also the more expensive model on tokens at $0.40 input / $2.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Gemma 4 E2B. That is roughly Infinityx on output cost alone. Gemma 4 E2B is the reasoning model in the pair, while Mistral Medium 3 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 | Mistral Medium 3 |
|---|---|---|
| Agentic | ||
| Coming soon | ||
| CodingGemma 4 E2B wins | ||
| LiveCodeBench | 44% | 30.3% |
| HumanEval | — | 92.1% |
| Multimodal & Grounded | ||
| MMMU-Pro | 44.2% | — |
| Reasoning | ||
| BBH | 21.9% | — |
| MRCRv2 | 19.1% | — |
| KnowledgeMistral Medium 3 wins | ||
| GPQA | 43.4% | 57.1% |
| MMLU-Pro | 60% | 77.2% |
| Instruction Following | ||
| IFEval | — | 89.4% |
| Multilingual | ||
| Coming soon | ||
| Mathematics | ||
| MATH-500 | — | 91% |
Mistral Medium 3 is ahead overall, 53 to 39. The biggest single separator in this matchup is MMLU-Pro, where the scores are 60% and 77.2%.
Mistral Medium 3 has the edge for knowledge tasks in this comparison, averaging 70.1 versus 54.1. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
Gemma 4 E2B has the edge for coding in this comparison, averaging 44 versus 30.3. Inside this category, LiveCodeBench 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.