Ctrl K
Back to models

LG AI Research

EXAONE 4.5 33B

  • Released
  • Open weights
  • EXAONE AI Model License Agreement 1.2 - NC
Compare
Intelligence Index

Reasoning setting

13.2
Estimated · Artificial Analysis v4.3.2
Context window
262.14K tok

Performance profile

ReasoningRank #53 of 107
79.4%
GPQA Diamond

Capabilities

Context window

Modalities

Measured setting

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
ReasoningEstimated
Intelligence Index
13.2

Pricing & access

No API offering listed in our tracked sources.

Run locally

Original download
68.7 GB
App memory
Unverified
Documented software
vLLMSetup guide (opens in a new tab)
Find GGUF downloads (opens in a new tab)Original weights (opens in a new tab)

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

EXAONE 4.5 33B · Reasoning#81 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 78Qwen3.5 Omni PlusStandard14.9%
  6. 79K2 Horizon 3.7BReasoning13.9%
  7. 80Mistral Medium 3.5High13.8%
  8. 81EXAONE 4.5 33BReasoning12.9%
  9. 82Qwen3 Next 80B A3B (Reasoning)Reasoning12.6%
  10. 83Command A+Reasoning12.0%
  11. 84Nova 2.0 LiteHigh11.6%

Peers use their best measured result on this benchmark.