Mistral Large 3 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

Mistral Large 3· Sarvam 105B

Quick Verdict

Pick Sarvam 105B if you want the stronger benchmark profile. Mistral Large 3 only becomes the better choice if instruction following is the priority or you would rather avoid the extra latency and token burn of a reasoning model.

Sarvam 105B has the cleaner overall profile here, landing at 60 versus 58. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Sarvam 105B's sharpest advantage is in knowledge, where it averages 81.7 against 48.1. The single biggest benchmark swing on the page is AIME 2025, 77% to 88.3%. Mistral Large 3 does hit back in instruction following, so the answer changes if that is the part of the workload you care about most.

Mistral Large 3 is also the more expensive model on tokens at $2.00 input / $6.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Sarvam 105B. That is roughly Infinityx on output cost alone. Sarvam 105B is the reasoning model in the pair, while Mistral Large 3 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.

Operational tradeoffs

Price$2.00 / $6.00Free*
Speed48 t/sN/A
TTFT1.04sN/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.

BenchmarkMistral Large 3Sarvam 105B
AgenticSarvam 105B wins
OSWorld-Verified49%
BrowseComp49.5%
CodingSarvam 105B wins
HumanEval92.3%
SWE-bench Verified45%45%
LiveCodeBench39%
SWE-bench Pro42%
LiveCodeBench v671.7%
Multimodal & Grounded
MMMU-Pro75%
OfficeQA Pro76%
Reasoning
MuSR71%
BBH81%
LongBench v267%
MRCRv267%
gpqaDiamond78.7%
hle11.2%
KnowledgeSarvam 105B wins
GPQA43.9%
SuperGPQA73%
MMLU-Pro73.1%81.7%
HLE12%
FrontierScience67%
SimpleQA24%
MMLU90.6%
Instruction FollowingMistral Large 3 wins
IFEval89.4%84.8%
Multilingual
MGSM82%
MMLU-ProX77%
MathematicsSarvam 105B wins
AIME 202376%
AIME 202478%
AIME 202577%88.3%
HMMT Feb 202372%
HMMT Feb 202474%
HMMT Feb 202573%
BRUMO 202575%
MATH-50093.6%98.6%
HMMT Feb 202585.8%
HMMT Nov 202585.8%
Frequently Asked Questions (6)

Which is better, Mistral Large 3 or Sarvam 105B?

Sarvam 105B is ahead overall, 60 to 58. The biggest single separator in this matchup is AIME 2025, where the scores are 77% and 88.3%.

Which is better for knowledge tasks, Mistral Large 3 or Sarvam 105B?

Sarvam 105B has the edge for knowledge tasks in this comparison, averaging 81.7 versus 48.1. Inside this category, MMLU-Pro is the benchmark that creates the most daylight between them.

Which is better for coding, Mistral Large 3 or Sarvam 105B?

Sarvam 105B has the edge for coding in this comparison, averaging 45 versus 41.5. Mistral Large 3 stays close enough that the answer can still flip depending on your workload.

Which is better for math, Mistral Large 3 or Sarvam 105B?

Sarvam 105B has the edge for math in this comparison, averaging 92.3 versus 80.4. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Mistral Large 3 or Sarvam 105B?

Sarvam 105B has the edge for agentic tasks in this comparison, averaging 49.5 versus 49. Mistral Large 3 stays close enough that the answer can still flip depending on your workload.

Which is better for instruction following, Mistral Large 3 or Sarvam 105B?

Mistral Large 3 has the edge for instruction following in this comparison, averaging 89.4 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.