Tier
Moderate
Headquarters
Seoul, South Korea
Founded
2020
Flagship
EXAONE
Models tracked
8
Artificial Analysis
Top intelligence
32.1
Artificial Analysis Index
Cheapest model
$0.00
blended /1M
Fastest output
0
tokens / sec
Flagship
LG AI Research’s top-scoring model on the Artificial Analysis Intelligence Index.
Most intelligent model
K-EXAONE (Reasoning)
Released 2025-12-31
Intelligence
32.1
Coding
27.0
Math
90.3
In $/1M
$0.00
Out $/1M
$0.00
Speed t/s
0
Benchmark breakdown
Models & benchmarks
Every LG AI Research model on file — intelligence, coding, price, and speed.
| Model | Released | Intel | Coding | Math | In $/1M | Out $/1M | Speed t/s | Latency s |
|---|---|---|---|---|---|---|---|---|
| K-EXAONE (Reasoning) | 2025-12-31 | 32.1 | 27.0 | 90.3 | $0.00 | $0.00 | 0 | 0.00 |
| EXAONE 4.5 33B | 2026-04-09 | 30.2 | 23.0 | — | $0.00 | $0.00 | 0 | 0.00 |
| K-EXAONE (Non-reasoning) | 2025-12-31 | 23.4 | 13.5 | 44.0 | $0.00 | $0.00 | 0 | 0.00 |
| EXAONE 4.0 32B (Reasoning) | 2025-07-15 | 16.7 | 14.0 | 80.0 | $0.00 | $0.00 | 0 | 0.00 |
| EXAONE 4.0 32B (Non-reasoning) | 2025-07-15 | 11.7 | 9.4 | 39.3 | $0.00 | $0.00 | 0 | 0.00 |
| Exaone 4.0 1.2B (Reasoning) | 2025-07-15 | 8.3 | 3.1 | 50.3 | $0.00 | $0.00 | 0 | 0.00 |
| Exaone 4.0 1.2B (Non-reasoning) | 2025-07-15 | 8.1 | 2.5 | 24.0 | $0.00 | $0.00 | 0 | 0.00 |
| EXAONE 4.5 33B (Non-reasoning) | 2026-04-09 | — | — | — | $0.00 | $0.00 | 0 | 0.00 |
Trajectory
LG AI Research’s model releases over time, by intelligence.
House strengths
Where LG AI Research’s lineup over-indexes, averaged across its models.
Capability profile
Best value
No pricing data to rank value.
Overview
The dedicated AI research arm of LG, producing the EXAONE family of bilingual enterprise and reasoning models.
Visit LG AI Research