# Exaone 4.0 32B Benchmark Scores & Performance

> Exaone 4.0 32B by LG AI Research scores 38.95/100 overall, ranking #181 out of 497 AI models.

Canonical page: https://benchlm.ai/models/exaone-4-0-32b

Last updated: September 21, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | LG AI Research |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 128K |
| Overall Score | 38.95/100 |
| Overall Rank | #181 of 497 |

## Family & Coverage

- Family: Exaone 4.0
- Variant: 32b
- Benchmarks covered: 11 of 447
- Sibling models: [Exaone 4.0 1.2B](/models/exaone-4-0-1-2b)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [τ²-bench results](/benchmarks/tau2-bench) | 4.1% |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [CritPt](/benchmarks/critpt) | 0.0% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [MMLU-Pro](/benchmarks/mmlu-pro) | 81.8% |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 6.3% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 62.8% |
| [AA-HLE](/benchmarks/aahle) | 5.0% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -62.8% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 10.6% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 82.1% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-IFBench](/benchmarks/aaifbench) | 33.5% |

## Mathematics Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AIME 2025](/benchmarks/aime2025) | 85.3% |

## Other LG AI Research Models

- [K-Exaone](/models/k-exaone) - Score: 43.19
- [Exaone 4.0 1.2B](/models/exaone-4-0-1-2b) - Score: 38.37
- [K-EXAONE 2.0](/models/k-exaone-2-0) - Score: not computed