What are K-EXAONE's benchmark scores?

As of 25 Oct 2026, K-EXAONE (thinking effort) scores 49.6 ±7.5 on the BenchLeader Index, strongest in instruction following (64) and weakest in knowledge (35). That rests on 6 independent benchmark results, and every score on this page links to its publisher.

How does K-EXAONE rank?

K-EXAONE (thinking effort) is #390 of 785 ranked configurations on 25 Oct 2026. 431 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

When was K-EXAONE released?

LG AI Research released K-EXAONE on 31 Dec 2025. BenchLeader has results for it at 2 reasoning-effort settings.

LG AI ResearchOpen weightsCompare with another model

K-EXAONE

Reasoning effort

K-EXAONE is a LG AI Research open-weights model, released 31 Dec 2025. Its best configuration (thinking reasoning effort) ranks #390 of 785 on the BenchLeader Index at 49.6 ±7.5, in the upper half. The ± is the point: 431 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (64) and lowest in knowledge (35). It has been measured at 2 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 31 Dec 2025.stale: no new result in six months

Blended price: –
Output speed: –
First answer: –
Context: 256k
Full answer: –
Cost per run: –
Released: 31 Dec 2025

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

Overall index50
Reasoning43
Agents & tools54
Knowledge35
Instruction following64
Long context55
Composite46

Versions

LG AI Research has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

Model	Released	Index	Rank
K Exaone 2.0 0803	12 Aug 2026	49.5	#396
K-EXAONEthinkingthis page	31 Dec 2025	49.6	#390

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. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.

Effort	Index	Rank	Speed	First answer	Chat reply cost	Categories
no reasoning	44.2	#545	–	–	–	Agents & tools 40 · Composite 42 · Instruction following 42 · Knowledge 32 · Long context 51 · Reasoning 41
thinkingbest	49.6	#390	–	–	–	Agents & tools 54 · Composite 46 · Instruction following 64 · Knowledge 35 · Long context 55 · Reasoning 43

How its index has moved

9 Sept 2026 to 21 Oct 2026

thinking
no reasoning

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. 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	no reasoning	thinking	Source
GPQA Diamond (AA)not in index	69.5%#303	78.3%#211	Artificial Analysis
Humanity's Last Exam (AA)not in index	5.7%#417	13.9%#262	Artificial Analysis
CritPt	0.0%#315	1.1%#236	Artificial Analysis

Coding

Benchmark	thinking	Source
Terminal-Bench 2.1 (AA)not in index	30.3%#153	Artificial Analysis

Agents & tools

Benchmark	no reasoning	thinking	Source
Terminal-Bench Hard	6.8%#249	22.7%#153	Artificial Analysis
τ²-Bench Telecom (AA)not in index	59.1%#182	74.3%#141	Artificial Analysis

Knowledge

Benchmark	no reasoning	thinking	Source
AA-Omniscience	-65.4#501	-58.0#449	Artificial Analysis
AA-Omniscience: accuracynot in index	13.7%#452	16.4%#392	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	8.4%#460	11.2%#394	Artificial Analysis

Instruction following

Benchmark	no reasoning	thinking	Source
IFBench	39.6%#265	64.7%#106	Artificial Analysis

Long context

Benchmark	no reasoning	thinking	Source
AA-LCR	53.3%#307	61.3%#273	Artificial Analysis

Composite

Benchmark	no reasoning	thinking	Source
AA Intelligence Index v4.3.2	11.2#358	14.4#295	Artificial Analysis

New this month

Questions people ask

What are K-EXAONE's benchmark scores?: As of 25 Oct 2026, K-EXAONE (thinking effort) scores 49.6 ±7.5 on the BenchLeader Index, strongest in instruction following (64) and weakest in knowledge (35). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
How does K-EXAONE rank?: K-EXAONE (thinking effort) is #390 of 785 ranked configurations on 25 Oct 2026. 431 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was K-EXAONE released?: LG AI Research released K-EXAONE on 31 Dec 2025. BenchLeader has results for it at 2 reasoning-effort settings.

Data as of 25 Oct 2026. Compare these configurations.

Cite as: BenchLeader, “K-EXAONE: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/k-exaone.