Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
DeepSeekMath V2
63
Winner · 2/8 categoriesSarvam 105B
60
3/8 categoriesDeepSeekMath V2· Sarvam 105B
Pick DeepSeekMath V2 if you want the stronger benchmark profile. Sarvam 105B only becomes the better choice if mathematics is the priority.
DeepSeekMath V2 has the cleaner overall profile here, landing at 63 versus 60. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
DeepSeekMath V2's sharpest advantage is in agentic, where it averages 63.9 against 49.5. The single biggest benchmark swing on the page is BrowseComp, 66% to 49.5%. Sarvam 105B does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.
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 | DeepSeekMath V2 | Sarvam 105B |
|---|---|---|
| AgenticDeepSeekMath V2 wins | ||
| Terminal-Bench 2.0 | 65% | — |
| BrowseComp | 66% | 49.5% |
| OSWorld-Verified | 61% | — |
| CodingDeepSeekMath V2 wins | ||
| HumanEval | 72% | — |
| SWE-bench Verified | 45% | 45% |
| LiveCodeBench | 44% | — |
| SWE-bench Pro | 51% | — |
| LiveCodeBench v6 | — | 71.7% |
| Multimodal & Grounded | ||
| MMMU-Pro | 64% | — |
| OfficeQA Pro | 73% | — |
| Reasoning | ||
| MuSR | 75% | — |
| BBH | 86% | — |
| LongBench v2 | 75% | — |
| MRCRv2 | 72% | — |
| gpqaDiamond | — | 78.7% |
| hle | — | 11.2% |
| KnowledgeSarvam 105B wins | ||
| GPQA | 79% | — |
| SuperGPQA | 77% | — |
| FrontierScience | 73% | — |
| SimpleQA | 77% | — |
| MMLU | — | 90.6% |
| MMLU-Pro | — | 81.7% |
| Instruction FollowingSarvam 105B wins | ||
| IFEval | 83% | 84.8% |
| Multilingual | ||
| MGSM | 87% | — |
| MMLU-ProX | 80% | — |
| MathematicsSarvam 105B wins | ||
| AIME 2024 | 82% | — |
| AIME 2025 | 81% | 88.3% |
| HMMT Feb 2023 | 76% | — |
| HMMT Feb 2024 | 78% | — |
| HMMT Feb 2025 | 77% | — |
| BRUMO 2025 | 79% | — |
| MATH-500 | 90% | 98.6% |
| HMMT Feb 2025 | — | 85.8% |
| HMMT Nov 2025 | — | 85.8% |
DeepSeekMath V2 is ahead overall, 63 to 60. The biggest single separator in this matchup is BrowseComp, where the scores are 66% and 49.5%.
Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 76.1. DeepSeekMath V2 stays close enough that the answer can still flip depending on your workload.
DeepSeekMath V2 has the edge for coding in this comparison, averaging 46.9 versus 45. Sarvam 105B 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 82.6. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
DeepSeekMath V2 has the edge for agentic tasks in this comparison, averaging 63.9 versus 49.5. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
Sarvam 105B has the edge for instruction following in this comparison, averaging 84.8 versus 83. 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.