Hy-Backend 2.0

In use

Coding agents complete Tencent in-house backend development tasks in the Claude Code scaffold. Task and scoring details are not published.

Tencent runs it with Claude Code for all models except GPT models, which use Codex.

Models scored in lab cards

Launch posts list it, from 1 lab

Tencent Hy4 preview leads with 35.2%

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

Source: Labs’ model cards

#	Model	Score	Setting	Date	Source
1	Tencent Hy4 preview	35.2%		Aug 2026	Lab model card
2	Tencent Hy3	25%		Jul 2026	Lab model card

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 Best so far

Source: Labs’ model cards

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
Aug 28, 2026	Tencent Hy4 preview	35.2	Hy-Backend 2.0 (Internal)
Jul 2, 2026	Tencent Hy3	25	Hy-Backend 2.0 (internal)