Gemini 2.5 Flash vs Sarvam 30B

Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.

Agentic
Coding
Multimodal & Grounded
Reasoning
Knowledge
Instruction Following
Multilingual
Mathematics

Gemini 2.5 Flash· Sarvam 30B

Quick Verdict

Pick Gemini 2.5 Flash if you want the stronger benchmark profile. Sarvam 30B only becomes the better choice if knowledge is the priority or you want the cheaper token bill.

Gemini 2.5 Flash has the cleaner overall profile here, landing at 50 versus 48. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Gemini 2.5 Flash's sharpest advantage is in agentic, where it averages 46.5 against 35.5. The single biggest benchmark swing on the page is HumanEval, 42% to 92.1%. Sarvam 30B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

Gemini 2.5 Flash is also the more expensive model on tokens at $0.15 input / $0.60 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Sarvam 30B. That is roughly Infinityx on output cost alone. Sarvam 30B is the reasoning model in the pair, while Gemini 2.5 Flash is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Gemini 2.5 Flash gives you the larger context window at 1M, compared with 64K for Sarvam 30B.

Operational tradeoffs

ProviderGoogleSarvam
Price$0.15 / $0.60Free*
Speed221 t/sN/A
TTFT0.50sN/A
Context1M64K

Decision framing

BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.

Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.

BenchmarkGemini 2.5 FlashSarvam 30B
AgenticGemini 2.5 Flash wins
Terminal-Bench 2.044%
BrowseComp58%35.5%
OSWorld-Verified41%
Claw-Eval27.9%
CodingSarvam 30B wins
HumanEval42%92.1%
SWE-bench Verified23%34%
LiveCodeBench18%
SWE-bench Pro25%
LiveCodeBench v670.0%
Multimodal & Grounded
MMMU-Pro69%
OfficeQA Pro66%
Reasoning
MuSR46%
BBH75%
LongBench v268%
MRCRv268%
gpqaDiamond66.5%
KnowledgeSarvam 30B wins
GPQA49%
SuperGPQA47%
FrontierScience49%
SimpleQA48%
MMLU85.1%
MMLU-Pro80%
Instruction Following
IFEval79%
Multilingual
MGSM74%
MMLU-ProX69%
MathematicsSarvam 30B wins
AIME 202350%
AIME 202452%
AIME 202551%80%
HMMT Feb 202346%
HMMT Feb 202448%
HMMT Feb 202547%
BRUMO 202549%
MATH-50072%97%
HMMT Feb 202573.3%
HMMT Nov 202574.2%
Frequently Asked Questions (5)

Which is better, Gemini 2.5 Flash or Sarvam 30B?

Gemini 2.5 Flash is ahead overall, 50 to 48. The biggest single separator in this matchup is HumanEval, where the scores are 42% and 92.1%.

Which is better for knowledge tasks, Gemini 2.5 Flash or Sarvam 30B?

Sarvam 30B has the edge for knowledge tasks in this comparison, averaging 80 versus 48.3. Gemini 2.5 Flash stays close enough that the answer can still flip depending on your workload.

Which is better for coding, Gemini 2.5 Flash or Sarvam 30B?

Sarvam 30B has the edge for coding in this comparison, averaging 34 versus 21.8. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Gemini 2.5 Flash or Sarvam 30B?

Sarvam 30B has the edge for math in this comparison, averaging 86.5 versus 55.6. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Gemini 2.5 Flash or Sarvam 30B?

Gemini 2.5 Flash has the edge for agentic tasks in this comparison, averaging 46.5 versus 35.5. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Last updated: April 3, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.