- MMLU (0.87) 87
- ARC-C (0.95) 95
- TriviaQA (0.91) 91
- GPQA Diamond (0.48) 48
- HumanEval (0.88) 88
- MBPP (0.75) 75
- GSM-8K (0.94) 94
- MATH (0.81) 81
- IFEval (0.87) 87
- MTBench 8.14
- IndicGenBench (0.49) 49
- MILU-IN, Indic queries only (0.75) 75
Sarvam-M
Sarvam-M places in the top three on TriviaQA.
12
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Sarvam AI May 2025
Sarvam-M
Open weights Flagship
No Epoch Capabilities Index score yet
- IFEval 87% #56 /126
- MMLU 87% #41 /127
- HumanEval 88% #26 /95
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 | |
|---|---|---|---|---|
| TriviaQA | 91% | #2 of 39 | Model card | |
| ARC-Challenge | 95% | #6 of 45 | Model card | |
| MMLU | 87% | #41 of 127 | Model card | |
| IFEval | 87% | #56 of 126 | Model card | |
| MT-Bench | 8.14 | #21 of 23 | Model card | |
| IndicGenBench | 37.2 | #12 of 13 | Official leaderboard | |
| MILU | 75% | #10 of 10 | Model card |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH | 81% | #20 of 93 | Model card | |
| GSM8K | 94% | #20 of 87 | Model card | |
| GPQA Diamond | 48% | #237 of 284 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.