Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Mistral Medium 3
~53
1/8 categoriesSarvam 105B
60
Winner · 3/8 categoriesMistral Medium 3· Sarvam 105B
Pick Sarvam 105B if you want the stronger benchmark profile. Mistral Medium 3 only becomes the better choice if instruction following is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Sarvam 105B is clearly ahead on the aggregate, 60 to 53. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Sarvam 105B's sharpest advantage is in coding, where it averages 45 against 30.3. The single biggest benchmark swing on the page is MATH-500, 91% to 98.6%. Mistral Medium 3 does hit back in instruction following, 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 Sarvam 105B. That is roughly Infinityx on output cost alone. Sarvam 105B 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 | Mistral Medium 3 | Sarvam 105B |
|---|---|---|
| Agentic | ||
| BrowseComp | — | 49.5% |
| CodingSarvam 105B wins | ||
| HumanEval | 92.1% | — |
| LiveCodeBench | 30.3% | — |
| LiveCodeBench v6 | — | 71.7% |
| SWE-bench Verified | — | 45% |
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| gpqaDiamond | — | 78.7% |
| hle | — | 11.2% |
| KnowledgeSarvam 105B wins | ||
| GPQA | 57.1% | — |
| MMLU-Pro | 77.2% | 81.7% |
| MMLU | — | 90.6% |
| Instruction FollowingMistral Medium 3 wins | ||
| IFEval | 89.4% | 84.8% |
| Multilingual | ||
| Coming soon | ||
| MathematicsSarvam 105B wins | ||
| MATH-500 | 91% | 98.6% |
| AIME 2025 | — | 88.3% |
| HMMT Feb 2025 | — | 85.8% |
| HMMT Nov 2025 | — | 85.8% |
Sarvam 105B is ahead overall, 60 to 53. The biggest single separator in this matchup is MATH-500, where the scores are 91% and 98.6%.
Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 70.1. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
Sarvam 105B has the edge for coding in this comparison, averaging 45 versus 30.3. Mistral Medium 3 stays close enough that the answer can still flip depending on your workload.
Sarvam 105B has the edge for math in this comparison, averaging 92.3 versus 91. 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 84.8. 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.