Qwen3.5 397B 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

Qwen3.5 397B· Sarvam 30B

Quick Verdict

Pick Qwen3.5 397B if you want the stronger benchmark profile. Sarvam 30B only becomes the better choice if knowledge is the priority or you want the stronger reasoning-first profile.

Qwen3.5 397B is clearly ahead on the aggregate, 68 to 48. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.5 397B's sharpest advantage is in agentic, where it averages 58.3 against 35.5. The single biggest benchmark swing on the page is SWE-bench Verified, 76.2% to 34%. Sarvam 30B does hit back in knowledge, 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 Qwen3.5 397B 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. Qwen3.5 397B gives you the larger context window at 128K, compared with 64K for Sarvam 30B.

Operational tradeoffs

PriceFree*Free*
Speed96 t/sN/A
TTFT2.44sN/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.

BenchmarkQwen3.5 397BSarvam 30B
AgenticQwen3.5 397B wins
Terminal-Bench 2.052.5%
BrowseComp62%35.5%
OSWorld-Verified62.2%
Claw-Eval48.1%
QwenClawBench51.8%
QwenWebBench1162
TAU3-Bench68.4%
DeepPlanning37.6%
Toolathlon36.3%
MCP Atlas46.1%
MCP-Tasks74.2%
WideResearch74.0%
CodingQwen3.5 397B wins
HumanEval75%92.1%
SWE-bench Verified76.2%34%
LiveCodeBench39%
LiveCodeBench v683.6%70.0%
SWE-bench Pro50.9%
SWE Multilingual69.3%
NL2Repo32.2%
Multimodal & Grounded
MMMU-Pro79%
OfficeQA Pro68%
RealWorldQA83.9%
Video-MME (w/o subtitle)84.2%
MathVision88.6%
We-Math87.9%
DynaMath86.3%
MStar83.8%
SimpleVQA67.1%
ChatCVQA80.8%
AI2D_TEST93.9%
CountBench97.2%
RefCOCO (avg)92.3%
ODINW1347.0%
MLVU (M-Avg)86.7%
ScreenSpot Pro65.6%
Reasoning
MuSR78%
BBH82%
LongBench v263.2%
MRCRv271%
AI-Needle68.7%
gpqaDiamond66.5%
KnowledgeSarvam 30B wins
MMLU83%85.1%
GPQA88.4%
SuperGPQA70.4%
MMLU-Pro87.8%80%
MMLU-Redux94.9%
C-Eval93%
HLE28.7%
FrontierScience71%
SimpleQA80%
Instruction Following
IFEval92.6%
IFBench76.5%
Multilingual
MGSM82%
MMLU-ProX84.7%
NOVA-6359.1%
INCLUDE85.6%
PolyMath73.3%
VWT2k-lite78.9%
MAXIFE88.2%
MathematicsSarvam 30B wins
AIME 202383%
AIME 202485%
AIME 202584%80%
AIME2693.3%
HMMT Feb 202379%
HMMT Feb 202481%
HMMT Feb 202580%
HMMT Feb 202594.8%73.3%
HMMT Nov 202592.7%74.2%
HMMT Feb 202687.9%
MMAnswerBench80.9%
BRUMO 202582%
MATH-50081%97%
Frequently Asked Questions (5)

Which is better, Qwen3.5 397B or Sarvam 30B?

Qwen3.5 397B is ahead overall, 68 to 48. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 76.2% and 34%.

Which is better for knowledge tasks, Qwen3.5 397B or Sarvam 30B?

Sarvam 30B has the edge for knowledge tasks in this comparison, averaging 80 versus 68.2. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3.5 397B or Sarvam 30B?

Qwen3.5 397B has the edge for coding in this comparison, averaging 52.2 versus 34. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Qwen3.5 397B or Sarvam 30B?

Sarvam 30B has the edge for math in this comparison, averaging 86.5 versus 82.6. Inside this category, HMMT Feb 2025 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3.5 397B or Sarvam 30B?

Qwen3.5 397B has the edge for agentic tasks in this comparison, averaging 58.3 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.