Sarvam 30B vs Z-1

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

Agentic
Coding
Multimodal & Grounded
Reasoning
Knowledge
Instruction Following
Multilingual
Mathematics

Sarvam 30B· Z-1

Quick Verdict

Pick Sarvam 30B if you want the stronger benchmark profile. Z-1 only becomes the better choice if agentic is the priority or you need the larger 128K context window.

Sarvam 30B is clearly ahead on the aggregate, 48 to 44. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Sarvam 30B's sharpest advantage is in knowledge, where it averages 80 against 42.1. The single biggest benchmark swing on the page is HumanEval, 92.1% to 44%. Z-1 does hit back in agentic, 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 Z-1 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. Z-1 gives you the larger context window at 128K, compared with 64K for Sarvam 30B.

Operational tradeoffs

ProviderSarvamZ
PriceFree*Pricing unavailable
SpeedN/AN/A
TTFTN/AN/A
Context64K128K

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.

BenchmarkSarvam 30BZ-1
AgenticZ-1 wins
BrowseComp35.5%49%
Terminal-Bench 2.039%
OSWorld-Verified41%
CodingSarvam 30B wins
HumanEval92.1%44%
LiveCodeBench v670.0%
SWE-bench Verified34%33%
LiveCodeBench22%
SWE-bench Pro30%
Multimodal & Grounded
MMMU-Pro46%
OfficeQA Pro56%
Reasoning
gpqaDiamond66.5%
MuSR48%
BBH74%
LongBench v256%
MRCRv257%
KnowledgeSarvam 30B wins
MMLU85.1%52%
MMLU-Pro80%64%
SuperGPQA49%
HLE6%
FrontierScience51%
SimpleQA50%
Instruction Following
IFEval80%
Multilingual
MGSM74%
MMLU-ProX72%
MathematicsSarvam 30B wins
MATH-50097%73%
AIME 202580%53%
HMMT Feb 202573.3%
HMMT Nov 202574.2%
AIME 202352%
AIME 202454%
HMMT Feb 202348%
HMMT Feb 202450%
HMMT Feb 202549%
BRUMO 202551%
Frequently Asked Questions (5)

Which is better, Sarvam 30B or Z-1?

Sarvam 30B is ahead overall, 48 to 44. The biggest single separator in this matchup is HumanEval, where the scores are 92.1% and 44%.

Which is better for knowledge tasks, Sarvam 30B or Z-1?

Sarvam 30B has the edge for knowledge tasks in this comparison, averaging 80 versus 42.1. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Sarvam 30B or Z-1?

Sarvam 30B has the edge for coding in this comparison, averaging 34 versus 27.6. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Sarvam 30B or Z-1?

Sarvam 30B has the edge for math in this comparison, averaging 86.5 versus 57.3. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Sarvam 30B or Z-1?

Z-1 has the edge for agentic tasks in this comparison, averaging 42.2 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.