DeepSeek V3.2 (Thinking) 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

DeepSeek V3.2 (Thinking)· Sarvam 105B

Quick Verdict

Pick DeepSeek V3.2 (Thinking) if you want the stronger benchmark profile. Sarvam 105B only becomes the better choice if knowledge is the priority.

DeepSeek V3.2 (Thinking) is clearly ahead on the aggregate, 67 to 60. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

DeepSeek V3.2 (Thinking)'s sharpest advantage is in agentic, where it averages 69.4 against 49.5. The single biggest benchmark swing on the page is BrowseComp, 70% to 49.5%. Sarvam 105B does hit back in knowledge, 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.

BenchmarkDeepSeek V3.2 (Thinking)Sarvam 105B
AgenticDeepSeek V3.2 (Thinking) wins
Terminal-Bench 2.071%
BrowseComp70%49.5%
OSWorld-Verified67%
DeepPlanning27.4%
CodingDeepSeek V3.2 (Thinking) wins
HumanEval79%
SWE-bench Verified48%45%
LiveCodeBench45%
SWE-bench Pro58%
LiveCodeBench v671.7%
Multimodal & Grounded
MMMU-Pro66%
Reasoning
MuSR81%
BBH86%
LongBench v278%
MRCRv278%
ARC-AGI-24%
gpqaDiamond78.7%
hle11.2%
KnowledgeSarvam 105B wins
MMLU87%90.6%
GPQA85%
SuperGPQA83%
MMLU-Pro73%81.7%
HLE22%
FrontierScience77%
SimpleQA83%
Instruction FollowingDeepSeek V3.2 (Thinking) wins
IFEval85%84.8%
Multilingual
MGSM84%
MMLU-ProX79%
MathematicsSarvam 105B wins
AIME 202387%
AIME 202489%
AIME 202588%88.3%
HMMT Feb 202383%
HMMT Feb 202485%
HMMT Feb 202584%
BRUMO 202586%
MATH-50084%98.6%
HMMT Feb 202585.8%
HMMT Nov 202585.8%
Frequently Asked Questions (6)

Which is better, DeepSeek V3.2 (Thinking) or Sarvam 105B?

DeepSeek V3.2 (Thinking) is ahead overall, 67 to 60. The biggest single separator in this matchup is BrowseComp, where the scores are 70% and 49.5%.

Which is better for knowledge tasks, DeepSeek V3.2 (Thinking) or Sarvam 105B?

Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 65.9. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for coding, DeepSeek V3.2 (Thinking) or Sarvam 105B?

DeepSeek V3.2 (Thinking) has the edge for coding in this comparison, averaging 50.7 versus 45. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, DeepSeek V3.2 (Thinking) or Sarvam 105B?

Sarvam 105B has the edge for math in this comparison, averaging 92.3 versus 86.3. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, DeepSeek V3.2 (Thinking) or Sarvam 105B?

DeepSeek V3.2 (Thinking) has the edge for agentic tasks in this comparison, averaging 69.4 versus 49.5. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for instruction following, DeepSeek V3.2 (Thinking) or Sarvam 105B?

DeepSeek V3.2 (Thinking) has the edge for instruction following in this comparison, averaging 85 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.