← All models
Compare

DeepSeek-V4-Pro-0813 vs K-EXAONE

DeepSeek-V4-Pro-0813 (DeepSeek) and K-EXAONE (LG AI Research) compared on benchmarks, pricing, context window, and use-case rankings.

AttributeDeepSeek-V4-Pro-0813DeepSeek · 1 in the newsK-EXAONELG AI Research
Scores
Intelligence (ECI)155
Coding7826
Math8851
Reasoning & Knowledge6928
Agentic & Tools21
Specifications
DeveloperDeepSeekLG AI Research
FamilyDeepSeek
ReleasedAug 13, 2026Dec 31, 2025
Parameters1.6T236B
AvailabilityOpen weights (unrestricted)Open weights (restricted use)
Context window1M
Price — $/M input$0.58
Price — $/M output$1.74
Inputstext
Outputstext
Benchmarks
AIME 2024/202599%90%
ARC-AGI91%
ARC-AGI-261%
GPQA Diamond92%78%
Humanity's Last Exam41%14%
SciCode51%36%
SimpleQA Verified53%
WebDev Arena1582
WeirdML66%
LiveCodeBench77%
MMLU-Pro84%
τ²-bench74%

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, DeepSeek-V4-Pro-0813 or K-EXAONE?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, DeepSeek-V4-Pro-0813 ranks higher — 78th vs 26th 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.