---
title: "EXAONE Deep 32B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for EXAONE Deep."
source: "https://rankedagi.com/models/exaone-deep-32b"
---

# EXAONE Deep

| Field | Value |
| --- | --- |
| Organization | LG |
| License | Proprietary |
| Size | 32B |
| Version | Latest |
| Released | 2025-03-18 |
| Last updated | 2025-04-16 22:54:48.259655+00 |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 46.0% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 43.0% | RankedAGI Agentic Score |  |
| LiveCodeBench v5 | coding | 59.5% | LiveCodeBench - Evaluation of Large Language Models for Code |  |
| RankedAGI Reasoning | reasoning | 49.2% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 66.1% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| AIME 2025 | math | 80.0% | AIME 2025 Competition Math |  |
| AIME 2024 | math | 90.0% | AIME 2024 Competition Math |  |
| MMLU Pro | knowledge | 74.0% | Graduate-level visual problem-solving |  |
| MMLU | knowledge | 83.0% | Image Reasoning |  |
| RankedAGI Math | math | 68.3% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 48.4% | Overall RankedAGI score |  |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://www.lgresearch.ai/blog/view?seq=543 |