Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-4o
50
0/8 categoriesSarvam 105B
60
Winner · 5/8 categoriesGPT-4o· Sarvam 105B
Pick Sarvam 105B if you want the stronger benchmark profile. GPT-4o only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
Sarvam 105B is clearly ahead on the aggregate, 60 to 50. 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 knowledge, where it averages 81.7 against 43.6. The single biggest benchmark swing on the page is SWE-bench Verified, 20% to 45%.
GPT-4o is also the more expensive model on tokens at $2.50 input / $10.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Sarvam 105B. That is roughly Infinityx on output cost alone. Sarvam 105B is the reasoning model in the pair, while GPT-4o 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 | GPT-4o | Sarvam 105B |
|---|---|---|
| AgenticSarvam 105B wins | ||
| Terminal-Bench 2.0 | 49% | — |
| OSWorld-Verified | 48% | — |
| BrowseComp | — | 49.5% |
| CodingSarvam 105B wins | ||
| HumanEval | 58% | — |
| SWE-bench Verified | 20% | 45% |
| LiveCodeBench | 38% | — |
| SWE-bench Pro | 29% | — |
| LiveCodeBench v6 | — | 71.7% |
| Multimodal & Grounded | ||
| OfficeQA Pro | 70% | — |
| VideoMMMU | 61.2% | — |
| Reasoning | ||
| MuSR | 62% | — |
| BBH | 82% | — |
| LongBench v2 | 62% | — |
| MRCRv2 | 63% | — |
| gpqaDiamond | — | 78.7% |
| hle | — | 11.2% |
| KnowledgeSarvam 105B wins | ||
| MMLU | 66% | 90.6% |
| GPQA | 66% | — |
| MMLU-Pro | 64% | 81.7% |
| HLE | 1% | — |
| FrontierScience | 58% | — |
| Instruction FollowingSarvam 105B wins | ||
| IFEval | 82% | 84.8% |
| Multilingual | ||
| MMLU-ProX | 72% | — |
| MathematicsSarvam 105B wins | ||
| AIME 2023 | 66% | — |
| AIME 2024 | 68% | — |
| AIME 2025 | 67% | 88.3% |
| HMMT Feb 2023 | 62% | — |
| HMMT Feb 2024 | 64% | — |
| BRUMO 2025 | 65% | — |
| MATH-500 | — | 98.6% |
| HMMT Feb 2025 | — | 85.8% |
| HMMT Nov 2025 | — | 85.8% |
Sarvam 105B is ahead overall, 60 to 50. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 20% and 45%.
Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 43.6. 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 30.4. 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 66.1. Inside this category, AIME 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 48.5. GPT-4o stays close enough that the answer can still flip depending on your workload.
Sarvam 105B has the edge for instruction following in this comparison, averaging 84.8 versus 82. 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.