Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 8B
~50
0/8 categoriesMistral Medium 3
~52
Winner · 3/8 categories1-bit Bonsai 8B· Mistral Medium 3
Pick Mistral Medium 3 if you want the stronger benchmark profile. 1-bit Bonsai 8B only becomes the better choice if you want the cheaper token bill.
Mistral Medium 3 has the cleaner overall profile here, landing at 52 versus 50. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Mistral Medium 3's sharpest advantage is in knowledge, where it averages 70.1 against 30. The single biggest benchmark swing on the page is GPQA, 30% 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 8B. That is roughly Infinityx on output cost alone. Mistral Medium 3 gives you the larger context window at 128K, compared with 64K for 1-bit Bonsai 8B.
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 8B | Mistral Medium 3 |
|---|---|---|
| Agentic | ||
| Coming soon | ||
| Coding | ||
| HumanEval | — | 92.1% |
| LiveCodeBench | — | 30.3% |
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| MuSR | 50% | — |
| KnowledgeMistral Medium 3 wins | ||
| GPQA | 30% | 57.1% |
| MMLU-Pro | — | 77.2% |
| Instruction FollowingMistral Medium 3 wins | ||
| IFEval | 79.8% | 89.4% |
| Multilingual | ||
| Coming soon | ||
| MathematicsMistral Medium 3 wins | ||
| MATH-500 | 66% | 91% |
Mistral Medium 3 is ahead overall, 52 to 50. The biggest single separator in this matchup is GPQA, where the scores are 30% and 57.1%.
Mistral Medium 3 has the edge for knowledge tasks in this comparison, averaging 70.1 versus 30. 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 66. 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 79.8. 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.