Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 4B
~44
0/8 categoriesMistral Medium 3
~52
Winner · 3/8 categories1-bit Bonsai 4B· Mistral Medium 3
Pick Mistral Medium 3 if you want the stronger benchmark profile. 1-bit Bonsai 4B only becomes the better choice if you want the cheaper token bill.
Mistral Medium 3 is clearly ahead on the aggregate, 52 to 44. 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 28.7. The single biggest benchmark swing on the page is GPQA, 28.7% to 57.1%.
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 1-bit Bonsai 4B. That is roughly Infinityx on output cost alone. Mistral Medium 3 gives you the larger context window at 128K, compared with 32K for 1-bit Bonsai 4B.
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 | 1-bit Bonsai 4B | Mistral Medium 3 |
|---|---|---|
| Agentic | ||
| Coming soon | ||
| Coding | ||
| HumanEval | — | 92.1% |
| LiveCodeBench | — | 30.3% |
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| MuSR | 41.4% | — |
| KnowledgeMistral Medium 3 wins | ||
| GPQA | 28.7% | 57.1% |
| MMLU-Pro | — | 77.2% |
| Instruction FollowingMistral Medium 3 wins | ||
| IFEval | 69.6% | 89.4% |
| Multilingual | ||
| Coming soon | ||
| MathematicsMistral Medium 3 wins | ||
| MATH-500 | 65.8% | 91% |
Mistral Medium 3 is ahead overall, 52 to 44. The biggest single separator in this matchup is GPQA, where the scores are 28.7% and 57.1%.
Mistral Medium 3 has the edge for knowledge tasks in this comparison, averaging 70.1 versus 28.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Mistral Medium 3 has the edge for math in this comparison, averaging 91 versus 65.8. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
Mistral Medium 3 has the edge for instruction following in this comparison, averaging 89.4 versus 69.6. Inside this category, IFEval 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.