Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
MiMo-V2-Pro
~85
Winner · 3/8 categoriesSarvam 30B
48
0/8 categoriesMiMo-V2-Pro· Sarvam 30B
Pick MiMo-V2-Pro if you want the stronger benchmark profile. Sarvam 30B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
MiMo-V2-Pro is clearly ahead on the aggregate, 85 to 48. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
MiMo-V2-Pro's sharpest advantage is in agentic, where it averages 86.7 against 35.5. The single biggest benchmark swing on the page is SWE-bench Verified, 78% to 34%.
MiMo-V2-Pro gives you the larger context window at 1M, compared with 64K for Sarvam 30B.
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 | MiMo-V2-Pro | Sarvam 30B |
|---|---|---|
| AgenticMiMo-V2-Pro wins | ||
| Terminal-Bench 2.0 | 86.7% | — |
| Claw-Eval | 61.5% | — |
| BrowseComp | — | 35.5% |
| CodingMiMo-V2-Pro wins | ||
| SWE-bench Verified | 78% | 34% |
| HumanEval | — | 92.1% |
| LiveCodeBench v6 | — | 70.0% |
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| gpqaDiamond | — | 66.5% |
| KnowledgeMiMo-V2-Pro wins | ||
| GPQA | 87% | — |
| MMLU | — | 85.1% |
| MMLU-Pro | — | 80% |
| Instruction Following | ||
| Coming soon | ||
| Multilingual | ||
| Coming soon | ||
| Mathematics | ||
| MATH-500 | — | 97% |
| AIME 2025 | — | 80% |
| HMMT Feb 2025 | — | 73.3% |
| HMMT Nov 2025 | — | 74.2% |
MiMo-V2-Pro is ahead overall, 85 to 48. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 78% and 34%.
MiMo-V2-Pro has the edge for knowledge tasks in this comparison, averaging 87 versus 80. Sarvam 30B stays close enough that the answer can still flip depending on your workload.
MiMo-V2-Pro has the edge for coding in this comparison, averaging 78 versus 34. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
MiMo-V2-Pro has the edge for agentic tasks in this comparison, averaging 86.7 versus 35.5. Sarvam 30B stays close enough that the answer can still flip depending on your workload.
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.