MMODELYST
Models/Sarvam M
MDL

Sarvam M

Sarvam

Verified against Artificial Analysis · Jul 13, 2026
Capability
38
percentile index
Price /M
$0 / $0
in / out
Context
Avg score
28.1
10 benchmarks
AA Intelligence
3.0
index
Weights
Closed
Released
May 23, 2025
About

Sarvam M is a proprietary model in the Sarvam family from Sarvam. Benchmarked on 10 evals, averaging 28.1.

Benchmark scores · 10
avg 28.1 — higher is better
MATH
84.7
MMLU-Pro
69.6
GPQA Diamond
41.6
IFBench
31.8
LiveCodeBench
29.5
SciCode
17.8
Humanity's Last Exam
3.3
Terminal-Bench Hard
2.3
τ²-bench
0
AA Long-Context Reasoning
0
The research behind this model
all papers mentioning it →

Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.

Details
PublisherSarvam
FamilySarvam
Parameters
License
WeightsClosed
ReleasedMay 23, 2025
Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$0/M