Sarvam 30B Benchmark Scores & Performance

BenchLM is tracking Sarvam 30B by Sarvam. Some benchmark data is visible, but not enough non-generated coverage is available for a leaderboard rank yet.

BenchLM is tracking Sarvam 30B, but this profile is currently excluded from the public leaderboard because it still lacks enough verified benchmark coverage to rank safely. Only verified public benchmark rows appear below.

Sarvam 30B is a open weight model with a 64K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

This profile currently has 11 of 126 tracked benchmarks. BenchLM only exposes verified benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Mathematics (#30). This performance profile makes it particularly strong for mathematical reasoning, scientific computing, and quantitative analysis.

Provider

Sarvam

Source Type

Open Weight

Reasoning

Reasoning

Context Window

64K

Model Status

Current

Release Date

Mar 6, 2026

Overall Score

Unranked

Pricing

$0.00 / $0.00

Input / output per 1M

Runtime

N/A

Latency unavailable

Rankings Overview

BenchLM is still missing enough verified benchmark coverage to rank this model across the public leaderboard. Only verified public benchmark rows are shown below.

Knowledge Benchmarks

MMLUStaleSaturatedDisplay onlyDetails
85.1%

MMLU · Static refresh · updated April 3, 2026

MMLU-ProRefreshingDetails
80%

MMLU-Pro · Static refresh · updated April 3, 2026

Coding Benchmarks

HumanEvalStaleSaturatedDisplay onlyDetails
92.1%

HumanEval · Static refresh · updated April 3, 2026

LiveCodeBench v6CurrentDisplay onlyDetails
70.0%

LiveCodeBench v6 2026 · Quarterly refresh · updated April 3, 2026

SWE-bench VerifiedRefreshingDetails
34%

SWE-bench Verified 2024 · Annual refresh · updated April 3, 2026

Mathematics Benchmarks

MATH-500StaleDetails
97%

MATH-500 2021 · Static refresh · updated April 3, 2026

AIME 2025CurrentDetails
80%

AIME 2025 · Annual refresh · updated April 3, 2026

HMMT Feb 2025CurrentDisplay onlyDetails
73.3%

HMMT Feb 2025 2025 · Quarterly refresh · updated April 3, 2026

HMMT Nov 2025CurrentDisplay onlyDetails
74.2%

HMMT Nov 2025 2025 · Quarterly refresh · updated April 3, 2026

Reasoning Benchmarks

gpqaDiamondRefreshingDisplay onlyDetails
66.5%

gpqaDiamond · Static refresh · updated April 3, 2026

Agentic Benchmarks

BrowseCompCurrentDetails
35.5%

BrowseComp 2026 · Quarterly refresh · updated April 3, 2026

Frequently Asked Questions

How does Sarvam 30B perform overall in AI benchmarks?

Sarvam 30B has 11 verified benchmark scores on BenchLM, but it does not yet have enough coverage to receive a global overall rank.

Is Sarvam 30B good for knowledge and understanding?

Sarvam 30B has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Sarvam 30B good for coding and programming?

Sarvam 30B has visible benchmark coverage in coding and programming, but BenchLM does not currently assign it a global category rank there.

Is Sarvam 30B good for mathematics?

Sarvam 30B ranks #30 out of 104 models in mathematics benchmarks with an average score of 86.5. There are stronger options in this category.

Is Sarvam 30B good for reasoning and logic?

Sarvam 30B has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Sarvam 30B good for agentic tool use and computer tasks?

Sarvam 30B has visible benchmark coverage in agentic tool use and computer tasks, but BenchLM does not currently assign it a global category rank there.

Is Sarvam 30B open source?

Yes, Sarvam 30B is an open weight model created by Sarvam, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Does Sarvam 30B have full benchmark coverage on BenchLM?

Not yet. Sarvam 30B currently has 11 verified benchmark scores out of the 126 benchmarks BenchLM tracks. BenchLM only exposes verified public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Sarvam 30B?

Sarvam 30B has a context window of 64K, which determines how much text it can process in a single interaction.

Last updated: April 3, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Weekly LLM Updates

New model releases, benchmark scores, and leaderboard changes. Every Friday.

Free. Your signup is stored with a derived country code for compliance routing.

More from Sarvam