What are Sarvam 30B's benchmark scores?

As of 25 Oct 2026, Sarvam 30B (high effort) scores 38.6 ±4.6 on the BenchLeader Index, strongest in reasoning (41) and weakest in long context (23). That rests on 6 independent benchmark results, and every score on this page links to its publisher.

How does Sarvam 30B rank?

Sarvam 30B (high effort) is #710 of 785 ranked configurations on 25 Oct 2026. 228 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

When was Sarvam 30B released?

Sarvam released Sarvam 30B on 6 Mar 2026.

SarvamOpen weightsReasoning modelCompare with another model

Sarvam 30B

Sarvam 30B is a Sarvam open-weights reasoning model, released 6 Mar 2026. Its best configuration (high reasoning effort) ranks #710 of 785 on the BenchLeader Index at 38.6 ±4.6, in the lower half. The ± is the point: 228 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in reasoning (41) and lowest in long context (23). Last measured 6 Mar 2026.stale: no new result in six months

Blended price: –
Output speed: –
First answer: –
Context: 66k
Full answer: –
Cost per run: –
Released: 6 Mar 2026

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index39
Reasoning41
Agents & tools36
Knowledge29
Instruction following31
Long context23
Composite37

How its index has moved

19 Sept 2026 to 21 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	high	Source
GPQA Diamond (AA)not in index	63.3%#355	Artificial Analysis
Humanity's Last Exam (AA)not in index	7.5%#363	Artificial Analysis
CritPt	0.3%#271	Artificial Analysis

Agents & tools

Benchmark	high	Source
Terminal-Bench Hard	2.3%#320	Artificial Analysis
τ²-Bench Telecom (AA)not in index	34.5%#238	Artificial Analysis

Knowledge

Benchmark	high	Source
AA-Omniscience	-71.5#518	Artificial Analysis
AA-Omniscience: accuracynot in index	12.6%#468	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	3.7%#541	Artificial Analysis

Instruction following

Benchmark	high	Source
IFBench	26.5%#385	Artificial Analysis

Long context

Benchmark	high	Source
AA-LCR	0.0%#493	Artificial Analysis

Composite

Benchmark	high	Source
AA Intelligence Index v4.3.2	6.6#522	Artificial Analysis

New this month

Questions people ask

What are Sarvam 30B's benchmark scores?: As of 25 Oct 2026, Sarvam 30B (high effort) scores 38.6 ±4.6 on the BenchLeader Index, strongest in reasoning (41) and weakest in long context (23). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
How does Sarvam 30B rank?: Sarvam 30B (high effort) is #710 of 785 ranked configurations on 25 Oct 2026. 228 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was Sarvam 30B released?: Sarvam released Sarvam 30B on 6 Mar 2026.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Sarvam 30B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/sarvam-30b.