GPT-OSS 120B 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

GPT-OSS 120B· Sarvam 30B

Quick Verdict

Pick GPT-OSS 120B if you want the stronger benchmark profile. Sarvam 30B only becomes the better choice if mathematics is the priority or you want the stronger reasoning-first profile.

GPT-OSS 120B 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.

GPT-OSS 120B's sharpest advantage is in agentic, where it averages 44.8 against 35.5. The single biggest benchmark swing on the page is HumanEval, 43% to 92.1%. Sarvam 30B does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.

Sarvam 30B is the reasoning model in the pair, while GPT-OSS 120B 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. GPT-OSS 120B gives you the larger context window at 128K, compared with 64K for Sarvam 30B.

Operational tradeoffs

ProviderOpenAISarvam
PriceFree*Free*
Speed262 t/sN/A
TTFT0.79sN/A
Context128K64K

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.

BenchmarkGPT-OSS 120BSarvam 30B
AgenticGPT-OSS 120B wins
Terminal-Bench 2.043%
BrowseComp50%35.5%
OSWorld-Verified43%
CodingSarvam 30B wins
HumanEval43%92.1%
SWE-bench Verified29%34%
LiveCodeBench25%
SWE-bench Pro31%
SWE-Rebench33.3%
React Native Evals66.4%
LiveCodeBench v670.0%
Multimodal & Grounded
MMMU-Pro42%
OfficeQA Pro57%
Reasoning
MuSR47%
BBH73%
LongBench v258%
MRCRv259%
gpqaDiamond66.5%
KnowledgeSarvam 30B wins
MMLU90%85.1%
GPQA80.9%
SuperGPQA48%
MMLU-Pro90%80%
HLE5%
FrontierScience49%
SimpleQA49%
Instruction Following
IFEval79%
Multilingual
MGSM72%
MMLU-ProX70%
MathematicsSarvam 30B wins
AIME 202351%
AIME 202453%
AIME 202552%80%
HMMT Feb 202347%
HMMT Feb 202449%
HMMT Feb 202548%
BRUMO 202550%
MATH-50071%97%
HMMT Feb 202573.3%
HMMT Nov 202574.2%
Frequently Asked Questions (5)

Which is better, GPT-OSS 120B or Sarvam 30B?

GPT-OSS 120B is ahead overall, 50 to 48. The biggest single separator in this matchup is HumanEval, where the scores are 43% and 92.1%.

Which is better for knowledge tasks, GPT-OSS 120B or Sarvam 30B?

Sarvam 30B has the edge for knowledge tasks in this comparison, averaging 80 versus 51.6. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for coding, GPT-OSS 120B or Sarvam 30B?

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

Which is better for math, GPT-OSS 120B or Sarvam 30B?

Sarvam 30B has the edge for math in this comparison, averaging 86.5 versus 56.1. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-OSS 120B or Sarvam 30B?

GPT-OSS 120B has the edge for agentic tasks in this comparison, averaging 44.8 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.