Benchmark Almanac

EXAONE Deep 32B

EXAONE Deep 32B.

LG AI Research Released March 18th, 2025 Family EXAONE Deep The lab's model card Compare with others
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

131.4 #266 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
  • LiveCodeBench v5 59.5% #26 /47
  • MMLU-Pro 74% #114 /167
  • 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% #61 of 131 Lab model card
MMLU-Pro 74% #114 of 167 Lab model card

Math and science

BenchmarkScoreRankSource
MATH-500 95.7% #37 of 70 Lab model card
AIME 2024 72.1% #58 of 88 Lab model card
GPQA Diamond 66.1% #200 of 302 Lab model card
AIME 2025 65.8% #117 of 143 Lab model card
CSAT Math 2025 94.5% #1 of 1 Lab model card

Coding

BenchmarkScoreRankSource
LiveCodeBench v5 59.5% #26 of 47 Lab model card

Its lab's numbers put it at 131.4, number 266 of 404

The Self-Reported Index fits one score to the 7 capability results LG AI Research reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 129.6 to 133.3. How we compute it.

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.