Benchmark Almanac

EXAONE Deep 32B

EXAONE Deep 32B.

LG AI Research Released 18 Mar 2025 Family EXAONE Deep The lab's model card
8
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
LG AI Research Mar 2025

EXAONE Deep 32B

Open weights Flagship

No Epoch Capabilities Index score yet
  • LiveCodeBench v5 59.5% #25 /44
  • MMLU-Pro 74% #105 /151
  • AIME 2025 65.8% #117 /143

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
MMLU 83% #59 of 127 Model card
MMLU-Pro 74% #105 of 151 Model card

Math and science

BenchmarkScoreRankSource
MATH-500 95.7% #37 of 67 Model card
AIME 2024 72.1% #57 of 87 Model card
GPQA Diamond 66.1% #188 of 284 Model card
AIME 2025 65.8% #117 of 143 Model card
CSAT Math 2025 94.5% #1 of 1 Model card

Coding

BenchmarkScoreRankSource
LiveCodeBench v5 59.5% #25 of 44 Model card

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it. 2 of them aren't in the launch post.