Kimi K2 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

Kimi K2· Sarvam 30B

Quick Verdict

Pick Kimi K2 if you want the stronger benchmark profile. Sarvam 30B only becomes the better choice if mathematics is the priority or you want the stronger reasoning-first profile.

Kimi K2 is clearly ahead on the aggregate, 53 to 48. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Kimi K2's sharpest advantage is in coding, where it averages 58.2 against 34. The single biggest benchmark swing on the page is SWE-bench Verified, 65.8% to 34%. Sarvam 30B does hit back in mathematics, 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 Kimi K2 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. Kimi K2 gives you the larger context window at 128K, compared with 64K for Sarvam 30B.

Operational tradeoffs

PricePricing unavailableFree*
Speed43 t/sN/A
TTFT1.51sN/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.

BenchmarkKimi K2Sarvam 30B
AgenticKimi K2 wins
Terminal-Bench 2.047.1%
BrowseComp60.2%35.5%
Tau2-Telecom66.1%
CodingKimi K2 wins
SWE-bench Verified65.8%34%
LiveCodeBench53.7%
HumanEval92.1%
LiveCodeBench v670.0%
Multimodal & Grounded
Coming soon
Reasoning
hle44.9%
gpqaDiamond66.5%
KnowledgeSarvam 30B wins
MMLU89.5%85.1%
GPQA75.1%
SuperGPQA57.2%
MMLU-Pro81.1%80%
SimpleQA31%
Instruction Following
IFEval89.8%
Multilingual
sweMultilingual61.1%
MathematicsSarvam 30B wins
AIME 202469.6%
AIME 202549.5%80%
MATH-50097.4%97%
HMMT Feb 202538.8%
HMMT Feb 202573.3%
HMMT Nov 202574.2%
Frequently Asked Questions (5)

Which is better, Kimi K2 or Sarvam 30B?

Kimi K2 is ahead overall, 53 to 48. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 65.8% and 34%.

Which is better for knowledge tasks, Kimi K2 or Sarvam 30B?

Sarvam 30B has the edge for knowledge tasks in this comparison, averaging 80 versus 64. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Kimi K2 or Sarvam 30B?

Kimi K2 has the edge for coding in this comparison, averaging 58.2 versus 34. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Kimi K2 or Sarvam 30B?

Sarvam 30B has the edge for math in this comparison, averaging 86.5 versus 67.9. Inside this category, AIME 2025 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Kimi K2 or Sarvam 30B?

Kimi K2 has the edge for agentic tasks in this comparison, averaging 52.1 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.