Sarvam 105B 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 105B· Z-1

Quick Verdict

Pick Sarvam 105B if you want the stronger benchmark profile. Z-1 only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.

Sarvam 105B is clearly ahead on the aggregate, 60 to 44. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Sarvam 105B's sharpest advantage is in knowledge, where it averages 81.7 against 42.1. The single biggest benchmark swing on the page is MMLU, 90.6% to 52%.

Sarvam 105B 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.

Operational tradeoffs

ProviderSarvamZ
PriceFree*Pricing unavailable
SpeedN/AN/A
TTFTN/AN/A
Context128K128K

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 105BZ-1
AgenticSarvam 105B wins
BrowseComp49.5%49%
Terminal-Bench 2.039%
OSWorld-Verified41%
CodingSarvam 105B wins
LiveCodeBench v671.7%
SWE-bench Verified45%33%
HumanEval44%
LiveCodeBench22%
SWE-bench Pro30%
Multimodal & Grounded
MMMU-Pro46%
OfficeQA Pro56%
Reasoning
gpqaDiamond78.7%
hle11.2%
MuSR48%
BBH74%
LongBench v256%
MRCRv257%
KnowledgeSarvam 105B wins
MMLU90.6%52%
MMLU-Pro81.7%64%
SuperGPQA49%
HLE6%
FrontierScience51%
SimpleQA50%
Instruction FollowingSarvam 105B wins
IFEval84.8%80%
Multilingual
MGSM74%
MMLU-ProX72%
MathematicsSarvam 105B wins
MATH-50098.6%73%
AIME 202588.3%53%
HMMT Feb 202585.8%
HMMT Nov 202585.8%
AIME 202352%
AIME 202454%
HMMT Feb 202348%
HMMT Feb 202450%
HMMT Feb 202549%
BRUMO 202551%
Frequently Asked Questions (6)

Which is better, Sarvam 105B or Z-1?

Sarvam 105B is ahead overall, 60 to 44. The biggest single separator in this matchup is MMLU, where the scores are 90.6% and 52%.

Which is better for knowledge tasks, Sarvam 105B or Z-1?

Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 42.1. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Sarvam 105B or Z-1?

Sarvam 105B has the edge for coding in this comparison, averaging 45 versus 27.6. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Sarvam 105B or Z-1?

Sarvam 105B has the edge for math in this comparison, averaging 92.3 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 105B or Z-1?

Sarvam 105B has the edge for agentic tasks in this comparison, averaging 49.5 versus 42.2. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for instruction following, Sarvam 105B or Z-1?

Sarvam 105B has the edge for instruction following in this comparison, averaging 84.8 versus 80. Inside this category, IFEval 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.