Qwen3.6 Plus 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

Qwen3.6 Plus· Sarvam 105B

Quick Verdict

Pick Qwen3.6 Plus if you want the stronger benchmark profile. Sarvam 105B only becomes the better choice if knowledge is the priority.

Qwen3.6 Plus is clearly ahead on the aggregate, 69 to 60. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.6 Plus's sharpest advantage is in coding, where it averages 64.9 against 45. The single biggest benchmark swing on the page is SWE-bench Verified, 78.8% to 45%. Sarvam 105B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

Qwen3.6 Plus gives you the larger context window at 1M, compared with 128K for Sarvam 105B.

Operational tradeoffs

PriceFree*Free*
SpeedN/AN/A
TTFTN/AN/A
Context1M128K

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.

BenchmarkQwen3.6 PlusSarvam 105B
AgenticQwen3.6 Plus wins
Terminal-Bench 2.061.6%
Claw-Eval58.7%
QwenClawBench57.2%
QwenWebBench1502
TAU3-Bench70.7%
VITA-Bench44.3%
DeepPlanning41.5%
Toolathlon39.8%
MCP Atlas48.2%
MCP-Tasks74.1%
WideResearch74.3%
OSWorld-Verified62.5%
BrowseComp49.5%
CodingQwen3.6 Plus wins
SWE-bench Verified78.8%45%
SWE-bench Pro56.6%
SWE Multilingual73.8%
LiveCodeBench v687.1%71.7%
NL2Repo37.9%
Multimodal & Grounded
MMMU86.0%
MMMU-Pro78.8%
RealWorldQA85.4%
OmniDocBench 1.591.2%
Video-MME (with subtitle)87.8%
Video-MME (w/o subtitle)84.2%
MathVision88.0%
We-Math89.0%
DynaMath88.0%
MStar83.3%
SimpleVQA67.3%
ChatCVQA81.5%
MMLongBench-Doc62.0%
CC-OCR83.4%
AI2D_TEST94.4%
CountBench97.6%
RefCOCO (avg)93.5%
ODINW1351.8%
ERQA65.7%
VideoMMMU84.0%
MLVU (M-Avg)86.7%
ScreenSpot Pro68.2%
Reasoning
AI-Needle68.3%
LongBench v262%
gpqaDiamond78.7%
hle11.2%
KnowledgeSarvam 105B wins
GPQA90.4%
SuperGPQA71.6%
MMLU-Pro88.5%81.7%
MMLU-Redux94.5%
C-Eval93.3%
HLE28.8%
MMLU90.6%
Instruction FollowingQwen3.6 Plus wins
IFEval94.3%84.8%
IFBench74.2%
Multilingual
MMLU-ProX84.7%
NOVA-6357.9%
INCLUDE85.1%
PolyMath77.4%
VWT2k-lite84.3%
MAXIFE88.2%
Mathematics
AIME2695.3%
HMMT Feb 202596.7%85.8%
HMMT Nov 202594.6%85.8%
HMMT Feb 202687.8%
MMAnswerBench83.8%
MATH-50098.6%
AIME 202588.3%
Frequently Asked Questions (5)

Which is better, Qwen3.6 Plus or Sarvam 105B?

Qwen3.6 Plus is ahead overall, 69 to 60. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 78.8% and 45%.

Which is better for knowledge tasks, Qwen3.6 Plus or Sarvam 105B?

Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 66. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen3.6 Plus or Sarvam 105B?

Qwen3.6 Plus has the edge for coding in this comparison, averaging 64.9 versus 45. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen3.6 Plus or Sarvam 105B?

Qwen3.6 Plus has the edge for agentic tasks in this comparison, averaging 62 versus 49.5. Sarvam 105B stays close enough that the answer can still flip depending on your workload.

Which is better for instruction following, Qwen3.6 Plus or Sarvam 105B?

Qwen3.6 Plus has the edge for instruction following in this comparison, averaging 94.3 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.