What is the IQ of K-EXAONE 2.0?

K-EXAONE 2.0 has an estimated IQ of 99, which ranks #121 out of 159 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.

Is K-EXAONE 2.0 open source?

Yes — K-EXAONE 2.0 is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.

When was K-EXAONE 2.0 released?

K-EXAONE 2.0 was publicly released on July 31, 2026.

How large is the context window of K-EXAONE 2.0?

K-EXAONE 2.0 supports a context window of 262,144 tokens — the amount of text it can consider in a single request.

LG AI Research

K-EXAONE 2.0

Public AI IQ model profile with source-backed benchmark results and derived ranking context.

IQ

99

EQ

n/a

Effective Cost

n/a

IQ Rank

#121

Release and Capabilities

Public release	2026-07-31
Modalities	text
Context window	262,144 tokens

Open weights on Hugging Face under Apache 2.0

Publisher-reported capabilities

K-EXAONE 2.0 scales LG AI Research's open family to 750B total and 37B active parameters.
It expands multilingual coverage to ten languages and targets reasoning, agentic coding, and long-context work.

Limitations and availability caveats

No durable hosted token price was published with the open-weight release.

Official release and model references

Measured Coverage and Estimates

K Exaone 2.0 has 6 of 39 tracked IQ benchmark inputs across 2 of 7 dimensions. Raw benchmark tables contain source-backed results only. Derived IQ combines all six dimensions using the shared scoring methodology, including estimates where direct coverage is incomplete.

Among dimensions with direct benchmark coverage, this profile's highest estimated scores are Academic Reasoning (IQ 115) and Reliability (IQ 109). These dimension estimates can include statistical adjustments or predecessor priors; they are not raw benchmark percentages or claims of real-world task success.

Benchmark versions, evaluation harnesses, and coverage affect comparisons; a missing result is not a score of zero. See the scoring methodology for estimation and uncertainty limits.

IQ Dimensions

Dimension	IQ	Coverage
Abstract Reasoning	88	0/5
Mathematical Reasoning	96	0/5
Academic Reasoning	115	4/6
Programmatic Reasoning	91	0/6
Computer Use	101	0/5
Reliability	109	2/6
Knowledge Work	94	0/6

Benchmark Results

Benchmark	Score	Dimension
AA Long Context Reasoning v1.1	60	Reliability
AA Omniscience	-6.6	Reliability
CritPt	0.8571	Academic Reasoning
GPQA Diamond	82.9293	Academic Reasoning
Humanity's Last Exam	18.582	Academic Reasoning
SciCode	42.0139	Academic Reasoning

Compare

Frequently Asked Questions

What is the IQ of K-EXAONE 2.0?: K-EXAONE 2.0 has an estimated IQ of 99, which ranks #121 out of 159 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
Is K-EXAONE 2.0 open source?: Yes — K-EXAONE 2.0 is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
When was K-EXAONE 2.0 released?: K-EXAONE 2.0 was publicly released on July 31, 2026.
How large is the context window of K-EXAONE 2.0?: K-EXAONE 2.0 supports a context window of 262,144 tokens — the amount of text it can consider in a single request.