Skip to main content

Sarvam 30B (high)

SarvamOpen WeightApache 2.0 · Commercial OK

Description

Sarvam-30B is an open-source 30B-parameter Mixture-of-Experts reasoning model from Sarvam AI trained from scratch and optimized for Indian languages, coding, and conversational workloads. It uses 128 sparse experts with 2.4B active parameters per token, Grouped Query Attention, and was pre-trained on 16 trillion tokens spanning code, mathematics, multilingual, and web data.

Release Date
2026-03-06
Parameters
30.0B
Context Length
66K
Modalities
text

Capability Radar

7
general
19
coding
63
reasoning
37
scienceest.
40
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agentic Capability109
36.0
LS
Code Ranking491
2.0
AA
General Ranking457
19.0
AA
Science321
35.0
AA

Benchmark Scores (LLM Stats)

Agents

BrowseComp35.5%SR

Biology

GPQA66.5%SR

Code

HumanEval92.1%SR
SWE-Bench Verified34.0%SR

Creativity

Arena-Hard v249.0%SR

Finance

MMLU85.1%SR
MMLU-Pro80.0%SR

General

MBPP0.93 / 100SR
LiveCodeBench v670.0%SR

Math

MATH-50097.0%SR
AIME 202596.7%SR
HMMT2574.2%SR
HMMT 202573.3%SR
Beyond AIME58.3%SR

AA Evaluation Indices

Intelligence Index
6.6
Gpqa
0.6
Tau2
0.3
Ifbench
0.3
Scicode
0.2
Hle
0.1
Terminalbench Hard
0.0
Lcr
0.0

LLM Stats Category Scores

Language
80
Legal
80
Math
80
Finance
80
Healthcare
80
Physics
70
Reasoning
70
General
70
Biology
70
Chemistry
70
Code
60
Creativity
50
Writing
50
Search
40
Agents
40
Frontend Development
30

Pricing

Input Price$0.026 / 1M tokens
Output Price$0.11 / 1M tokens
Blended Price (3:1)$0.047 / 1M tokens

Speed

Tokens/sec188.0
Time to First Token1.14s
Time to Answer11.78s

Provider Price Ranking

Provider Price Ranking

3 providers

Cheapest: FastRouterMost Expensive: NanoGPT
ProviderInputOutput
1FastRouterCheapest
$0.02
$0.1
2SarvamPRIMARY
$0.026
$0.11
3NanoGPT
$0.028
$0.111

Compare pricing across different API providers for this model.

External Sources