Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
o1-pro
45
1/8 categoriesSarvam 30B
48
Winner · 2/8 categorieso1-pro· Sarvam 30B
Pick Sarvam 30B if you want the stronger benchmark profile. o1-pro only becomes the better choice if agentic is the priority or you need the larger 200K context window.
Sarvam 30B has the cleaner overall profile here, landing at 48 versus 45. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Sarvam 30B's sharpest advantage is in coding, where it averages 34 against 23. The single biggest benchmark swing on the page is BrowseComp, 50% to 35.5%. o1-pro does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
o1-pro is also the more expensive model on tokens at $150.00 input / $600.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Sarvam 30B. That is roughly Infinityx on output cost alone. o1-pro gives you the larger context window at 200K, 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 | o1-pro | Sarvam 30B |
|---|---|---|
| Agentico1-pro wins | ||
| Terminal-Bench 2.0 | 40% | — |
| BrowseComp | 50% | 35.5% |
| OSWorld-Verified | 32% | — |
| CodingSarvam 30B wins | ||
| SWE-bench Pro | 23% | — |
| HumanEval | — | 92.1% |
| LiveCodeBench v6 | — | 70.0% |
| SWE-bench Verified | — | 34% |
| Multimodal & Grounded | ||
| MMMU-Pro | 48% | — |
| OfficeQA Pro | 49% | — |
| Reasoning | ||
| LongBench v2 | 54% | — |
| MRCRv2 | 59% | — |
| gpqaDiamond | — | 66.5% |
| KnowledgeSarvam 30B wins | ||
| GPQA | 79% | — |
| FrontierScience | 63% | — |
| MMLU | — | 85.1% |
| MMLU-Pro | — | 80% |
| Instruction Following | ||
| Coming soon | ||
| Multilingual | ||
| MMLU-ProX | 52% | — |
| Mathematics | ||
| AIME 2024 | 86% | — |
| MATH-500 | — | 97% |
| AIME 2025 | — | 80% |
| HMMT Feb 2025 | — | 73.3% |
| HMMT Nov 2025 | — | 74.2% |
Sarvam 30B is ahead overall, 48 to 45. The biggest single separator in this matchup is BrowseComp, where the scores are 50% and 35.5%.
Sarvam 30B has the edge for knowledge tasks in this comparison, averaging 80 versus 69.4. o1-pro stays close enough that the answer can still flip depending on your workload.
Sarvam 30B has the edge for coding in this comparison, averaging 34 versus 23. o1-pro stays close enough that the answer can still flip depending on your workload.
o1-pro has the edge for agentic tasks in this comparison, averaging 39.7 versus 35.5. Inside this category, BrowseComp 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.