HumanEval-COBOL (Cohere)

Cohere Command A 25.3%

Only in system cards

Models write COBOL versions of HumanEval problems, or translate COBOL solutions to Python. Unit tests score pass@1.

Cohere built it for the Command A report. The report does not say whether it is released.

Made by: Cohere
Released: April 2025
Kind: Function-level problems
Level: University
Scored: Checked automatically
Answers: Code

Last in a system card: April 2025
Last model added: April 2025

Paper arxiv.org

Model scored in lab cards

System card reports it, from 1 lab

Cohere Command A leads with 25.3%

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

25.3 Cohere Command A

1 Cohere Command A 25.3%

Source: Labs’ model cards

#	Model	Score	Setting	Date	Source
1	Cohere Command A	25.3%		Apr 2025	Lab 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

Source: Labs’ model cards

Labs report it only in system cards

We read the headline results of 522 launch posts from 52 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
Apr 1, 2025	Cohere Command A technical report	25.3	HumanEval COBOL generation (Table 12). COBOL to Python translation 55.7	Capabilities

Cohere Command A leads with 25.3%

Scores over time

Labs report it only in system cards

One system card reports it

More in Coding