# Exaone 4.0 1.2B Benchmark Scores & Performance

> Exaone 4.0 1.2B by LG AI Research scores 38.37/100 overall, ranking #185 out of 497 AI models.

Canonical page: https://benchlm.ai/models/exaone-4-0-1-2b

Last updated: September 21, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | LG AI Research |
| Source Type | Open Weight |
| Reasoning Type | Non-Reasoning |
| Context Window | 128K |
| Overall Score | 38.37/100 |
| Overall Rank | #185 of 497 |

## Family & Coverage

- Family: Exaone 4.0
- Variant: 1-2b
- Benchmarks covered: 10 of 447
- Sibling models: [Exaone 4.0 32B](/models/exaone-4-0-32b)
- 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) | 20.5% |

## Reasoning Benchmarks

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

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 5.2% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 42.4% |
| [AA-HLE](/benchmarks/aahle) | 5.7% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -82.1% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 5.0% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 91.7% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-IFBench](/benchmarks/aaifbench) | 25.3% |

## Other LG AI Research Models

- [K-Exaone](/models/k-exaone) - Score: 43.19
- [Exaone 4.0 32B](/models/exaone-4-0-32b) - Score: 38.95
- [K-EXAONE 2.0](/models/k-exaone-2-0) - Score: not computed