Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Claude 4.1 Opus Thinking
57
2/8 categoriesSarvam 105B
60
Winner · 1/8 categoriesClaude 4.1 Opus Thinking· Sarvam 105B
Pick Sarvam 105B if you want the stronger benchmark profile. Claude 4.1 Opus Thinking only becomes the better choice if agentic is the priority or you need the larger 200K context window.
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 49. The single biggest benchmark swing on the page is SWE-bench Verified, 74.5% to 45%. Claude 4.1 Opus Thinking does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
Claude 4.1 Opus Thinking gives you the larger context window at 200K, compared with 128K for Sarvam 105B.
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 | Claude 4.1 Opus Thinking | Sarvam 105B |
|---|---|---|
| AgenticClaude 4.1 Opus Thinking wins | ||
| BrowseComp | 54% | 49.5% |
| CodingClaude 4.1 Opus Thinking wins | ||
| SWE-bench Verified | 74.5% | 45% |
| LiveCodeBench | 45% | — |
| SWE-bench Pro | 29% | — |
| LiveCodeBench v6 | — | 71.7% |
| Multimodal & Grounded | ||
| OfficeQA Pro | 69% | — |
| Reasoning | ||
| MuSR | 72% | — |
| MRCRv2 | 74% | — |
| gpqaDiamond | — | 78.7% |
| hle | — | 11.2% |
| KnowledgeSarvam 105B wins | ||
| MMLU | 76% | 90.6% |
| GPQA | 80.9% | — |
| SuperGPQA | 72% | — |
| MMLU-Pro | 76% | 81.7% |
| HLE | 8% | — |
| FrontierScience | 41% | — |
| SimpleQA | 36% | — |
| Instruction Following | ||
| IFEval | — | 84.8% |
| Multilingual | ||
| MGSM | 82% | — |
| MMLU-ProX | 73% | — |
| Mathematics | ||
| AIME 2024 | 40% | — |
| HMMT Feb 2024 | 36% | — |
| HMMT Feb 2025 | 35% | — |
| MATH-500 | — | 98.6% |
| AIME 2025 | — | 88.3% |
| 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 SWE-bench Verified, where the scores are 74.5% and 45%.
Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 49. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Claude 4.1 Opus Thinking has the edge for coding in this comparison, averaging 45.7 versus 45. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Claude 4.1 Opus Thinking has the edge for agentic tasks in this comparison, averaging 54 versus 49.5. 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.