K-Exaone 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

K-Exaone· Sarvam 105B

Quick Verdict

Pick Sarvam 105B if you want the stronger benchmark profile. K-Exaone only becomes the better choice if coding is the priority or you need the larger 256K context window.

Sarvam 105B is clearly ahead on the aggregate, 60 to 50. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

K-Exaone gives you the larger context window at 256K, compared with 128K for Sarvam 105B.

Operational tradeoffs

PriceN/AFree*
SpeedN/AN/A
TTFTN/AN/A
Context256K128K

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.

BenchmarkK-ExaoneSarvam 105B
Agentic
BrowseComp49.5%
CodingK-Exaone wins
SWE-bench Verified49.4%45%
LiveCodeBench v671.7%
Multimodal & Grounded
Coming soon
Reasoning
gpqaDiamond78.7%
hle11.2%
Knowledge
MMLU90.6%
MMLU-Pro81.7%
Instruction Following
IFEval84.8%
Multilingual
Coming soon
Mathematics
MATH-50098.6%
AIME 202588.3%
HMMT Feb 202585.8%
HMMT Nov 202585.8%
Frequently Asked Questions (2)

Which is better, K-Exaone or Sarvam 105B?

Sarvam 105B is ahead overall, 60 to 50. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 49.4% and 45%.

Which is better for coding, K-Exaone or Sarvam 105B?

K-Exaone has the edge for coding in this comparison, averaging 49.4 versus 45. Inside this category, SWE-bench Verified 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.