Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GPT-4o
50
Winner · 1/8 categoriesSarvam 30B
48
3/8 categoriesGPT-4o· Sarvam 30B
Pick GPT-4o 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.
GPT-4o has the cleaner overall profile here, landing at 50 versus 48. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
GPT-4o's sharpest advantage is in agentic, where it averages 48.5 against 35.5. The single biggest benchmark swing on the page is HumanEval, 58% to 92.1%. Sarvam 30B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
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 30B. That is roughly Infinityx on output cost alone. Sarvam 30B 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. GPT-4o 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 | GPT-4o | Sarvam 30B |
|---|---|---|
| AgenticGPT-4o wins | ||
| Terminal-Bench 2.0 | 49% | — |
| OSWorld-Verified | 48% | — |
| BrowseComp | — | 35.5% |
| CodingSarvam 30B wins | ||
| HumanEval | 58% | 92.1% |
| SWE-bench Verified | 20% | 34% |
| LiveCodeBench | 38% | — |
| SWE-bench Pro | 29% | — |
| LiveCodeBench v6 | — | 70.0% |
| Multimodal & Grounded | ||
| OfficeQA Pro | 70% | — |
| VideoMMMU | 61.2% | — |
| Reasoning | ||
| MuSR | 62% | — |
| BBH | 82% | — |
| LongBench v2 | 62% | — |
| MRCRv2 | 63% | — |
| gpqaDiamond | — | 66.5% |
| KnowledgeSarvam 30B wins | ||
| MMLU | 66% | 85.1% |
| GPQA | 66% | — |
| MMLU-Pro | 64% | 80% |
| HLE | 1% | — |
| FrontierScience | 58% | — |
| Instruction Following | ||
| IFEval | 82% | — |
| Multilingual | ||
| MMLU-ProX | 72% | — |
| MathematicsSarvam 30B wins | ||
| AIME 2023 | 66% | — |
| AIME 2024 | 68% | — |
| AIME 2025 | 67% | 80% |
| HMMT Feb 2023 | 62% | — |
| HMMT Feb 2024 | 64% | — |
| BRUMO 2025 | 65% | — |
| MATH-500 | — | 97% |
| HMMT Feb 2025 | — | 73.3% |
| HMMT Nov 2025 | — | 74.2% |
GPT-4o is ahead overall, 50 to 48. The biggest single separator in this matchup is HumanEval, where the scores are 58% and 92.1%.
Sarvam 30B has the edge for knowledge tasks in this comparison, averaging 80 versus 43.6. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Sarvam 30B has the edge for coding in this comparison, averaging 34 versus 30.4. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Sarvam 30B has the edge for math in this comparison, averaging 86.5 versus 66.1. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.
GPT-4o has the edge for agentic tasks in this comparison, averaging 48.5 versus 35.5. Sarvam 30B stays close enough that the answer can still flip depending on your workload.
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.