LG AI ResearchReleased Dec 31, 2025
Open weights
k-exaone
Its best results are in Programmatic Reasoning (#85 of 177) and Mathematical Reasoning (#85 of 176); weakest in Knowledge Work (#151 of 176). Abstract Reasoning and Computer Use are estimated, because no results are published yet.
Composite IQ ?
97
Effective cost
$0.609/1M
$0.20 in · $0.80 out
Speed
Not measured
No speed data yet
Context
256Ktokens
256,000 tokens in
Evidence
5of 7 dims
11 of 39 benchmarks
IQ profile
Seven dimensions, averaged equally into Composite IQ
MeasuredEstimated95% range
#1 in dimensionTop-10 median
IQ dimensions
Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.
DimensionIQPosition · 70–160RankEvidencevs Top 10
k-exaone95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human
Benchmark results
11 of 39 Composite IQ benchmarks have a published result for k-exaone. Benchmarks without a result stay listed so gaps are visible.
Abstract Reasoning IQ 77 · estimatedNo published results0/5
No published results yet for Abstract Reasoning. The 77 shown is estimated from k-exaone's other dimensions and will be replaced as results come in. How estimates work
ARC-AGI-3ARC-AGI-2ARC-AGI-1Chess PuzzlesMystery Game Puzzles
Mathematical Reasoning IQ 112 · measuredBest: #26 of 56 on AIME1/5
BenchmarkScorePercentileRankLeader · source
Not yet reported
FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1MathArena
Academic Reasoning IQ 112 · measuredBest: #23 of 45 on MMLU-Pro5/6
BenchmarkScorePercentileRankLeader · source
MMLU-Pro
TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22
83.8%
#23 / 45
Leader fable-5.1 · 92.4%
TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22
TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22
GPQA Diamond
Artificial Analysis v4.3.2 · Oct 27
78.3%
#106 / 147
Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
CritPt
Artificial Analysis v4.3.2 · Oct 27
1.1%
#117 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Humanity's Last Exam
Artificial Analysis v4.3.2 · Oct 27
13.9%
#131 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
SciCode
Artificial Analysis model leaderboard · Sep 10
35.6%
#145 / 167
Leader opus-5.5 · 66.9%
Artificial Analysis model leaderboard · Sep 10
Artificial Analysis model leaderboard · Sep 10
Not yet reported
MMMU-Pro
Programmatic Reasoning IQ 113 · measuredBest: #42 of 61 on LiveCodeBench1/6
BenchmarkScorePercentileRankLeader · source
Not yet reported
IOI V2Terminal-Bench 4.0ProgramBenchSWE-rebenchMirrorCode
Computer Use IQ 75 · estimatedNo published results0/5
No published results yet for Computer Use. The 75 shown is estimated from k-exaone's other dimensions and will be replaced as results come in. How estimates work
BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam
Reliability IQ 103 · measuredBest: #60 of 96 on IFBench3/6
BenchmarkScorePercentileRankLeader · source
IFBench
Artificial Analysis v4.3.2 · Oct 27
64.7%
#60 / 96
Leader minimax-m3 · 82.9%
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
AA Long Context Reasoning v1.1
Artificial Analysis v4.3.2 · Oct 27
61.3%
#127 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
-58.0
#155 / 158
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
SimpleQA VerifiedBullshitBench v2FACTS Grounding
Knowledge Work IQ 91 · measuredBest: #111 of 124 on GDPval-AA v2.1 normalized score1/6
BenchmarkScorePercentileRankLeader · source
GDPval-AA v2.1 normalized score
Artificial Analysis v4.3.2 · Oct 20
0.0%
#111 / 124
Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 20
Artificial Analysis v4.3.2 · Oct 20
Not yet reported
AA-Briefcase v1.1AutomationBench-AAGDP.pdfAA-AnalystAgentEnterpriseOps-Gym-AA
Release & availability
Release details on record for this model.
- Released
- Developer
- LG AI Research
- Weights
- Open weightsDownloadable and self-hostable
- Context
- 256,000 tokens
- API price
- $0.20 in · $0.80 outper 1M tokens · full pricing
About this score
How much of k-exaone's IQ is measured, and how the rest is estimated.
11/ 39benchmark results
5/ 7dimensions measured
2estimated
0/5Abstract
1/5Math
5/6Academic
1/6Coding
0/5Computer Use
3/6Reliability
1/6Knowledge Work
Bar height = share of benchmarks with resultsEstimatedNo score
Measured results are shown as published
Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.
Estimates fill the gaps
Abstract Reasoning and Computer Use have no published results yet, so their IQ is estimated from k-exaone's other dimensions.
A missing result is not a zero
Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.
Compare k-exaone
Side-by-side pages for the models it is most often weighed against.
#1 overall
gpt-6.1-sol
IQ141 44 higherEffective cost$6.30 10.4× pricier
World (Other) #1
mistral-large-4
IQ119 22 higherEffective cost$4.69 7.7× pricier
Closest IQ
MiniCPM5 2B
IQ97 same IQ
Most similar profile
nova-2.0-pro
IQ97 same IQEffective cost$6.90 11.3× pricier
Similar price
mercury-2
IQ93 4 lowerEffective cost$0.631 about the same
#2 overall
opus-5.5
IQ141 44 higherEffective cost$35.73 58.7× pricier
k-exaoneComparison model
Frequently asked questions
Quick answers about k-exaone, drawn from the same data as the rest of this page.
How AI IQ scores models →Get this data from the API →- What is the IQ of k-exaone?
- k-exaone has an estimated IQ of 97, which ranks #140 out of 176 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.
- What is k-exaone best at?
- Among the dimensions with published benchmark results, k-exaone ranks highest in Programmatic Reasoning (IQ 113, #85 of 177) and Mathematical Reasoning (IQ 112, #85 of 176). Its lowest-ranked measured dimension is Knowledge Work (IQ 91, #151 of 176).
- What is the EQ of k-exaone?
- k-exaone doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for k-exaone. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
- Which benchmarks has k-exaone been tested on?
- k-exaone has published results on 11 of the 39 benchmarks behind AI IQ's Composite IQ, including AIME, MMLU-Pro, IFBench, LiveCodeBench and GPQA Diamond.
- How much does k-exaone cost?
- k-exaone costs $0.20 per million input tokens and $0.80 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.6087 per million input-plus-output tokens.
- Is k-exaone open source?
- Yes — k-exaone is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
- Who developed k-exaone?
- k-exaone was developed by LG AI Research, based in South Korea.
- When was k-exaone released?
- k-exaone was publicly released on December 31, 2025.
- How large is the context window of k-exaone?
- k-exaone supports a context window of 256,000 tokens — the amount of text it can consider in a single request.
- How fast is k-exaone?
- AI IQ doesn't have independent speed measurements for k-exaone yet. Speed comes from independent tests of a model's hosted API, which aren't available for every model — especially new, restricted-access, or self-hosted ones.