LG AI Research Open weights: LGAI-EXAONE/EXAONE-4.0-1.2BAuto-detected

Exaone 4.0 1.2B

Name: Exaone 4.0 1.2B benchmark results
Creator: BenchLeader

Best configuration ranks #563 of 610 on the BenchLeader Index at 37.3 ±3.9.

Blended price: –
Output speed: –
First answer: –
Context: 64k

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index37
Agents & tools34
Knowledge25
Instruction following30
Long context25
Composite36

Reasoning-effort configurations

The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Default” means the publisher did not say which setting was used.

Effort	Index	Rank	Speed	First answer	Chat reply cost	Categories
thinking	37.2	#566	–	–	–	Agents & tools 34 · Composite 36 · Instruction following 28 · Knowledge 26 · Long context 25
defaultbest	37.3	#563	–	–	–	Agents & tools 34 · Composite 36 · Instruction following 30 · Knowledge 25 · Long context 25

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	thinking	default	Source
GPQA Diamond (AA)not in index	51.5%#399	42.4%#444	Artificial Analysis
Humanity's Last Exam (AA)not in index	6.0%#334	5.7%#342	Artificial Analysis

Agents & tools

Benchmark	thinking	default	Source
Terminal-Bench Hard	0.0%#345	0.0%#345	Artificial Analysis
τ²-Bench Telecom (AA)not in index	16.4%#339	20.5%#319	Artificial Analysis

Knowledge

Benchmark	thinking	default	Source
AA-Omniscience	-79.8#458	-82.2#464	Artificial Analysis

Instruction following

Benchmark	thinking	default	Source
IFBench	23.0%#380	25.3%#373	Artificial Analysis

Long context

Benchmark	thinking	default	Source
AA-LCR	0.0%#419	0.0%#419	Artificial Analysis

Composite

Benchmark	thinking	default	Source
AA Intelligence Index	5.3#501	5.2#503	Artificial Analysis