Hy-Backend 2.0

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.

Made by Tencent Hy team Released Jul 2026 Fixing real repositories Tasks kept private Last in a launch post Aug 2026 Last model added Aug 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: Code A program or patch run against tests.

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

1 Tencent Hy4 preview 35.2%
2 Tencent Hy3 25%

#	Model	Score	Setting	Date	Source
1	Tencent Hy4 preview	35.2%		Aug 2026	Model card
2	Tencent Hy3	25%		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 Best so far

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

Versions

Replaces Hy-Backend

Tencent Hy4 preview leads with 35.2%

Scores over time

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

Versions

More in Coding