Hy-CompanyBench

Coding agents complete Tencent in-house company engineering tasks. Task and scoring details are not published.

Hy3 scored 41.7 here and 29.8 on V2, so the versions are not comparable.

Made by Tencent Hy team Released Jul 2026 Building whole projects Tasks kept private Last in a launch post Jul 2026 Last model added Jul 2026

Level: Expert Specialists with years of training, often over hours of work
Scored: Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers: Agent task Many steps in a terminal, browser, desktop, app, game or robot.

Model scored in lab cards

Launch post lists it, from 1 lab

Tencent Hy3 leads with 41.7%

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

41.7 Tencent Hy3

1 Tencent Hy3 41.7%

#	Model	Score	Setting	Date	Source
1	Tencent Hy3	41.7%		Jul 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

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Tencent

Date	Launch post	Score	As the post writes it
2 Jul 2026	Tencent Hy3	41.7	Hy-CompanyBench (internal)

Versions

Replaced by Hy-CompanyBench V2

Tencent Hy3 leads with 41.7%

Scores over time

One lab put it in a launch post in the last six months

Versions

More in Coding