CodeUtilityBench (LG)

K-EXAONE 71.9% Only in system cards

Models handle 16 everyday coding tasks such as explaining, debugging, refactoring and testing code. A GPT-5 judge checks five rubrics per item.

In-house LG AI Research evaluation. The tasks are not public.

Made by LG AI Research Released Jan 2026 Function-level problems Tasks kept private Last in a system card Jan 2026 Last model added Jan 2026

Level: University Undergraduates and entry-level professionals
Scored: Graded by a model A language model scores each response, usually against a rubric.
Answers: Open-ended Free-form text, documents, designs or media judged as a whole.

Paper

Model scored in lab cards

System card reports it, from 1 lab

K-EXAONE leads with 71.9%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

Bars Table

71.9 K-EXAONE

1 K-EXAONE 71.9%

#	Model	Score	Setting	Date	Source
1	K-EXAONE	71.9%		Jan 2026	Model card

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card

Labs report it only in system cards

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

Date	Document	Score	As the document writes it	Section
5 Jan 2026	K-EXAONE technical report	71.9	CodeUtilityBench (in-house) Overall, Reasoning. Understanding 75.6, Implementation 72.5, Refinement 67.3, Maintenance 61.0 (Figure 9 and D.1)	Capabilities

K-EXAONE leads with 71.9%

Scores over time

Labs report it only in system cards

One system card reports it

More in Coding