Qwen3 235B 2507 (Reasoning) vs Sarvam 105B

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

Agentic
Coding
Multimodal & Grounded
Reasoning
Knowledge
Instruction Following
Multilingual
Mathematics

Qwen3 235B 2507 (Reasoning)· Sarvam 105B

Quick Verdict

Pick Sarvam 105B if you want the stronger benchmark profile. Qwen3 235B 2507 (Reasoning) only becomes the better choice if instruction following is the priority.

Sarvam 105B is clearly ahead on the aggregate, 60 to 55. 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 50. The single biggest benchmark swing on the page is MMLU, 40% to 90.6%. Qwen3 235B 2507 (Reasoning) does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.

Operational tradeoffs

PriceFree*Free*
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.

BenchmarkQwen3 235B 2507 (Reasoning)Sarvam 105B
AgenticSarvam 105B wins
Terminal-Bench 2.047%
BrowseComp48%49.5%
CodingSarvam 105B wins
HumanEval32%
SWE-bench Verified16%45%
LiveCodeBench74.1%
SWE-bench Pro29%
LiveCodeBench v671.7%
Multimodal & Grounded
MMMU-Pro38%
OfficeQA Pro47%
Reasoning
MuSR36%
BBH63%
LongBench v258%
MRCRv258%
gpqaDiamond78.7%
hle11.2%
KnowledgeSarvam 105B wins
MMLU40%90.6%
GPQA81.1%
SuperGPQA64.9%
MMLU-Pro84.4%81.7%
HLE6%
FrontierScience42%
SimpleQA38%
Instruction FollowingQwen3 235B 2507 (Reasoning) wins
IFEval87.8%84.8%
Multilingual
MGSM62%
MMLU-ProX81%
MathematicsSarvam 105B wins
AIME 202340%
AIME 202442%
AIME 202592.3%88.3%
HMMT Feb 202336%
HMMT Feb 202438%
HMMT Feb 202537%
BRUMO 202539%
MATH-50060%98.6%
HMMT Feb 202585.8%
HMMT Nov 202585.8%
Frequently Asked Questions (6)

Which is better, Qwen3 235B 2507 (Reasoning) or Sarvam 105B?

Sarvam 105B is ahead overall, 60 to 55. The biggest single separator in this matchup is MMLU, where the scores are 40% and 90.6%.

Which is better for knowledge tasks, Qwen3 235B 2507 (Reasoning) or Sarvam 105B?

Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 50. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3 235B 2507 (Reasoning) or Sarvam 105B?

Sarvam 105B has the edge for coding in this comparison, averaging 45 versus 43.3. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Qwen3 235B 2507 (Reasoning) or Sarvam 105B?

Sarvam 105B has the edge for math in this comparison, averaging 92.3 versus 65.6. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3 235B 2507 (Reasoning) or Sarvam 105B?

Sarvam 105B has the edge for agentic tasks in this comparison, averaging 49.5 versus 47.4. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for instruction following, Qwen3 235B 2507 (Reasoning) or Sarvam 105B?

Qwen3 235B 2507 (Reasoning) has the edge for instruction following in this comparison, averaging 87.8 versus 84.8. 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.