- Math500 97
- Humaneval 92.1
- MBPP 92.7
- Live Code Bench v6 70
- MMLU 85.1
- MMLU Pro 80
- Arena Hard v2 49
- GPQA Diamond 66.5
- AIME 25 (80.0 without tools, 96.7 with tools) 80
- HMMT Feb 2025 73.3
- HMMT Nov 2025 74.2
- Beyond AIME 58.3
- BrowseComp 35.5
- SWE-Bench Verified 34
- Tau2 (avg.) 45.7
- Average pairwise win rate across all dimensions on the Indic benchmark (indivibe) 89
Sarvam 30B
Sarvam 30B ranks first on MBPP.
16
Benchmarks with a score
1
Ranked first, out of five or more models
1
In the top three
Sarvam AI Mar 2026
Sarvam 30B
Open weights Small
No Epoch Capabilities Index score yet
- BrowseComp 35.5% #70 /77
- tau2-bench 45.7% #68 /69
- MMLU-Pro 80% #76 /151
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMLU | 85.1% | #54 of 127 | Model card | |
| MMLU-Pro | 80% | #76 of 151 | Model card | |
| Arena-Hard v2.0 | 49% | #21 of 24 | Model card | |
| IndiVibe | 89% | #2 of 2 | Model card |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH-500 | 97% | #21 of 67 | Model card | |
| AIME 2025 | 80% | #89 of 143 | Model card | |
| GPQA Diamond | 66.5% | #186 of 284 | Model card | |
| Beyond AIME | 58.3% | #10 of 14 | Model card | |
| HMMT 2025 | 73.3% | #41 of 49 | Model card | |
| HMMT Nov 2025 | 74.2% | #23 of 23 | Model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MBPP | 92.7% | #1 of 66 | Model card | |
| HumanEval | 92.1% | #8 of 95 | Model card | |
| LiveCodeBench v6 | 70% | #48 of 76 | Model card | |
| SWE-bench Verified | 34% | #145 of 150 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BrowseComp | 35.5% | #70 of 77 | Model card | |
| tau2-bench | 45.7% | #68 of 69 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.