Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Sarvam 105B
60
Winner · 4/8 categoriesSarvam 30B
48
0/8 categoriesSarvam 105B· Sarvam 30B
Pick Sarvam 105B 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.
Sarvam 105B is clearly ahead on the aggregate, 60 to 48. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Sarvam 105B's sharpest advantage is in agentic, where it averages 49.5 against 35.5. The single biggest benchmark swing on the page is BrowseComp, 49.5% to 35.5%.
Sarvam 105B 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 | Sarvam 105B | Sarvam 30B |
|---|---|---|
| AgenticSarvam 105B wins | ||
| BrowseComp | 49.5% | 35.5% |
| CodingSarvam 105B wins | ||
| LiveCodeBench v6 | 71.7% | 70.0% |
| SWE-bench Verified | 45% | 34% |
| HumanEval | — | 92.1% |
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| gpqaDiamond | 78.7% | 66.5% |
| hle | 11.2% | — |
| KnowledgeSarvam 105B wins | ||
| MMLU | 90.6% | 85.1% |
| MMLU-Pro | 81.7% | 80% |
| Instruction Following | ||
| IFEval | 84.8% | — |
| Multilingual | ||
| Coming soon | ||
| MathematicsSarvam 105B wins | ||
| MATH-500 | 98.6% | 97% |
| AIME 2025 | 88.3% | 80% |
| HMMT Feb 2025 | 85.8% | 73.3% |
| HMMT Nov 2025 | 85.8% | 74.2% |
Sarvam 105B is ahead overall, 60 to 48. The biggest single separator in this matchup is BrowseComp, where the scores are 49.5% and 35.5%.
Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 80. 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 34. 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 86.5. Inside this category, HMMT Feb 2025 is the benchmark that creates the most daylight between them.
Sarvam 105B has the edge for agentic tasks in this comparison, averaging 49.5 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.