Qwen2.5-1M 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

Qwen2.5-1M· Sarvam 105B

Quick Verdict

Pick Qwen2.5-1M if you want the stronger benchmark profile. Sarvam 105B only becomes the better choice if knowledge is the priority or you want the stronger reasoning-first profile.

Qwen2.5-1M has the cleaner overall profile here, landing at 62 versus 60. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Qwen2.5-1M's sharpest advantage is in agentic, where it averages 64.7 against 49.5. The single biggest benchmark swing on the page is BrowseComp, 72% 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.

Sarvam 105B is the reasoning model in the pair, while Qwen2.5-1M 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. Qwen2.5-1M 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.

BenchmarkQwen2.5-1MSarvam 105B
AgenticQwen2.5-1M wins
Terminal-Bench 2.065%
BrowseComp72%49.5%
OSWorld-Verified59%
CodingQwen2.5-1M wins
HumanEval76%
SWE-bench Verified47%45%
LiveCodeBench40%
SWE-bench Pro49%
LiveCodeBench v671.7%
Multimodal & Grounded
MMMU-Pro63%
OfficeQA Pro75%
Reasoning
MuSR79%
BBH82%
LongBench v282%
MRCRv281%
gpqaDiamond78.7%
hle11.2%
KnowledgeSarvam 105B wins
MMLU84%90.6%
GPQA83%
SuperGPQA81%
MMLU-Pro74%81.7%
HLE10%
FrontierScience74%
SimpleQA81%
Instruction FollowingSarvam 105B wins
IFEval84%84.8%
Multilingual
MGSM81%
MMLU-ProX80%
MathematicsSarvam 105B wins
AIME 202385%
AIME 202487%
AIME 202586%88.3%
HMMT Feb 202381%
HMMT Feb 202483%
HMMT Feb 202582%
BRUMO 202584%
MATH-50083%98.6%
HMMT Feb 202585.8%
HMMT Nov 202585.8%
Frequently Asked Questions (6)

Which is better, Qwen2.5-1M or Sarvam 105B?

Qwen2.5-1M is ahead overall, 62 to 60. The biggest single separator in this matchup is BrowseComp, where the scores are 72% and 49.5%.

Which is better for knowledge tasks, Qwen2.5-1M or Sarvam 105B?

Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 62.1. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for coding, Qwen2.5-1M or Sarvam 105B?

Qwen2.5-1M has the edge for coding in this comparison, averaging 45.1 versus 45. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Qwen2.5-1M or Sarvam 105B?

Sarvam 105B has the edge for math in this comparison, averaging 92.3 versus 84.6. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Qwen2.5-1M or Sarvam 105B?

Qwen2.5-1M has the edge for agentic tasks in this comparison, averaging 64.7 versus 49.5. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for instruction following, Qwen2.5-1M or Sarvam 105B?

Sarvam 105B has the edge for instruction following in this comparison, averaging 84.8 versus 84. 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.