Benchmark Almanac

Hy-Vibe Bench

Coding agents complete development workflows drawn from real Tencent users. Task and scoring details are not published.

Seen only in the Hy3 preview card.

Made by
Tencent Hy team
Released
April 2026
Kind
Building whole projects
Level
Expert
Scored
Checked automatically
Answers
Code
Tasks
Kept private
Last in a launch post
April 2026, dropped before it saturated
Last model added
April 2026
1
Model scored in lab cards
1
Launch post lists it, from 1 lab

Tencent Hy3 preview leads with 50.5%

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.

  1. 1 Tencent Hy3 preview 50.5%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Tencent Hy3 preview 50.5% Apr 2026 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
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Tencent Hy3 preview 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Tencent Hy3 preview

Source: Labs’ model cards

Labs headline it less often now, last in April 2026

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
DateLaunch postScoreAs the post writes it
Apr 23, 2026 Tencent Hy3 preview 50.5 Hy-Vibe (internal)

More in Coding

All 282 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471