Ctrl K
Back to models

LG AI Research

K-EXAONE 2.0 0803

  • Released
  • Apache 2.0
Compare
Intelligence Index

Reasoning setting

19.7
Estimated · Artificial Analysis v4.3.2
Context window
262.14K tok

Performance profile

ReasoningRank #45 of 107
82.9%
GPQA Diamond
CodingRank #58 of 94
42.0%
SciCode

Capabilities

Context window

Modalities

Measured setting

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
ReasoningEstimated
Intelligence Index
19.7

Pricing & access

No API offering listed in our tracked sources.

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

K-EXAONE 2.0 0803 · Reasoning#70 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 67Gemma 4 26B A4BReasoning19.3%
  6. 68Gemini 3.5 Flash-LiteHigh18.8%
  7. 69Quasar 438BMax18.7%
  8. 70K-EXAONE 2.0 0803Reasoning18.6%
  9. 71K2 Horizon 7BReasoning18.2%
  10. 72G9v3-39A5BReasoning17.5%
  11. 73HyperNova 60B 2605High16.6%

Peers use their best measured result on this benchmark.