Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
K-Exaone
~50
Winner · 1/8 categoriesSarvam 30B
48
0/8 categoriesK-Exaone· Sarvam 30B
Pick K-Exaone if you want the stronger benchmark profile. Sarvam 30B only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
K-Exaone has the cleaner overall profile here, landing at 50 versus 48. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
K-Exaone's sharpest advantage is in coding, where it averages 49.4 against 34. The single biggest benchmark swing on the page is SWE-bench Verified, 49.4% to 34%.
K-Exaone gives you the larger context window at 256K, compared with 64K for Sarvam 30B.
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.
| Benchmark | K-Exaone | Sarvam 30B |
|---|---|---|
| Agentic | ||
| BrowseComp | — | 35.5% |
| CodingK-Exaone wins | ||
| SWE-bench Verified | 49.4% | 34% |
| HumanEval | — | 92.1% |
| LiveCodeBench v6 | — | 70.0% |
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| gpqaDiamond | — | 66.5% |
| Knowledge | ||
| MMLU | — | 85.1% |
| MMLU-Pro | — | 80% |
| Instruction Following | ||
| Coming soon | ||
| Multilingual | ||
| Coming soon | ||
| Mathematics | ||
| MATH-500 | — | 97% |
| AIME 2025 | — | 80% |
| HMMT Feb 2025 | — | 73.3% |
| HMMT Nov 2025 | — | 74.2% |
K-Exaone is ahead overall, 50 to 48. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 49.4% and 34%.
K-Exaone has the edge for coding in this comparison, averaging 49.4 versus 34. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
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.