Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
DeepSeek LLM 2.0
57
2/8 categoriesSarvam 105B
60
Winner · 3/8 categoriesDeepSeek LLM 2.0· Sarvam 105B
Pick Sarvam 105B if you want the stronger benchmark profile. DeepSeek LLM 2.0 only becomes the better choice if agentic is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Sarvam 105B has the cleaner overall profile here, landing at 60 versus 57. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Sarvam 105B's sharpest advantage is in knowledge, where it averages 81.7 against 59.1. The single biggest benchmark swing on the page is MATH-500, 83% to 98.6%. DeepSeek LLM 2.0 does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
Sarvam 105B is the reasoning model in the pair, while DeepSeek LLM 2.0 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 | DeepSeek LLM 2.0 | Sarvam 105B |
|---|---|---|
| AgenticDeepSeek LLM 2.0 wins | ||
| Terminal-Bench 2.0 | 57% | — |
| BrowseComp | — | 49.5% |
| CodingSarvam 105B wins | ||
| HumanEval | 73% | — |
| SWE-bench Verified | 46% | 45% |
| LiveCodeBench | 39% | — |
| SWE-bench Pro | 46% | — |
| LiveCodeBench v6 | — | 71.7% |
| Multimodal & Grounded | ||
| MMMU-Pro | 60% | — |
| OfficeQA Pro | 70% | — |
| Reasoning | ||
| BBH | 81% | — |
| gpqaDiamond | — | 78.7% |
| hle | — | 11.2% |
| KnowledgeSarvam 105B wins | ||
| MMLU | 79% | 90.6% |
| GPQA | 78% | — |
| SuperGPQA | 76% | — |
| MMLU-Pro | 72% | 81.7% |
| HLE | 12% | — |
| FrontierScience | 67% | — |
| SimpleQA | 77% | — |
| Instruction FollowingDeepSeek LLM 2.0 wins | ||
| IFEval | 85% | 84.8% |
| Multilingual | ||
| Coming soon | ||
| MathematicsSarvam 105B wins | ||
| AIME 2023 | 80% | — |
| AIME 2024 | 82% | — |
| AIME 2025 | 81% | 88.3% |
| HMMT Feb 2023 | 76% | — |
| HMMT Feb 2024 | 78% | — |
| HMMT Feb 2025 | 77% | — |
| MATH-500 | 83% | 98.6% |
| HMMT Feb 2025 | — | 85.8% |
| HMMT Nov 2025 | — | 85.8% |
Sarvam 105B is ahead overall, 60 to 57. The biggest single separator in this matchup is MATH-500, where the scores are 83% and 98.6%.
Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 59.1. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Sarvam 105B has the edge for coding in this comparison, averaging 45 versus 43.3. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Sarvam 105B has the edge for math in this comparison, averaging 92.3 versus 81.8. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
DeepSeek LLM 2.0 has the edge for agentic tasks in this comparison, averaging 57 versus 49.5. Sarvam 105B stays close enough that the answer can still flip depending on your workload.
DeepSeek LLM 2.0 has the edge for instruction following in this comparison, averaging 85 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.