Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
DeepSeek V3
49
Winner · 2/8 categoriesSarvam 30B
48
1/8 categoriesDeepSeek V3· Sarvam 30B
Pick DeepSeek V3 if you want the stronger benchmark profile. Sarvam 30B only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
DeepSeek V3 finishes one point ahead overall, 49 to 48. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
DeepSeek V3's sharpest advantage is in coding, where it averages 39.2 against 34. The single biggest benchmark swing on the page is SWE-bench Verified, 42% to 34%. Sarvam 30B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
DeepSeek V3 is also the more expensive model on tokens at $0.27 input / $1.10 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. Sarvam 30B is the reasoning model in the pair, while DeepSeek V3 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. DeepSeek V3 gives you the larger context window at 128K, 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 | DeepSeek V3 | Sarvam 30B |
|---|---|---|
| Agentic | ||
| BrowseComp | — | 35.5% |
| CodingDeepSeek V3 wins | ||
| LiveCodeBench | 37.6% | — |
| SWE-bench Verified | 42% | 34% |
| HumanEval | — | 92.1% |
| LiveCodeBench v6 | — | 70.0% |
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| LongBench v2 | 48.7% | — |
| gpqaDiamond | — | 66.5% |
| KnowledgeSarvam 30B wins | ||
| GPQA | 59.1% | — |
| MMLU-Pro | 75.9% | 80% |
| SimpleQA | 24.9% | — |
| MMLU | — | 85.1% |
| Instruction Following | ||
| IFEval | 86.1% | — |
| Multilingual | ||
| Coming soon | ||
| MathematicsDeepSeek V3 wins | ||
| AIME 2024 | 39.2% | — |
| MATH-500 | 90.2% | 97% |
| AIME 2025 | — | 80% |
| HMMT Feb 2025 | — | 73.3% |
| HMMT Nov 2025 | — | 74.2% |
DeepSeek V3 is ahead overall, 49 to 48. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 42% and 34%.
Sarvam 30B has the edge for knowledge tasks in this comparison, averaging 80 versus 57.5. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.
DeepSeek V3 has the edge for coding in this comparison, averaging 39.2 versus 34. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
DeepSeek V3 has the edge for math in this comparison, averaging 90.2 versus 86.5. Inside this category, MATH-500 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.