← All models
Compare

EXAONE 4.0 (32B) vs Kimi K3

EXAONE 4.0 (32B) (LG AI Research) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeEXAONE 4.0 (32B)LG AI ResearchKimi K3Moonshot · 35 in the news
Scores
Intelligence (ECI)157
Coding2499
Math1882
Reasoning & Knowledge1578
Agentic & Tools084
Specifications
DeveloperLG AI ResearchMoonshot
FamilyKimi
ReleasedJul 15, 2025Jul 16, 2026
Parameters32B2.8T
AvailabilityOpen weights (non-commercial)Open weights (non-commercial)
Context window1M
Price — $/M input$2.80
Price — $/M output$14.00
Inputstext, image, video
Outputstext
Benchmarks
AIME 2024/202580%97%
GPQA Diamond74%93%
Humanity's Last Exam11%47%
LiveCodeBench75%
MMLU-Pro82%
SciCode34%59%
τ²-bench17%
APEX39%
ARC-AGI95%
ARC-AGI-260%
SimpleQA Verified43%
WebDev Arena1682
WeirdML83%

Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.

Frequently asked questions

Which is better for coding, EXAONE 4.0 (32B) or Kimi K3?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 99th vs 24th percentile among the models tracked on Model Beat.

Want a different match-up? Open the compare tool to add or swap models.

Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.