E-Bench (Tencent)
Tencent Hy4 preview 77.1% In use Agents complete Tencent in-house work tasks in the working agent group. Task and scoring details are not published.
Not the Shanghai AI Lab robotics test EBench. Hy3 scored 50.2 in its own card and 48.5 in the Hy4 preview card after harness updates.
Made by Tencent Hy team Released Jul 2026 Documents and spreadsheets 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
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
2
Models scored in lab cards
2
Launch posts list it, from 1 lab
Tencent Hy4 preview leads with 77.1%
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 Tencent Hy4 preview 77.1%
- 2 Tencent Hy3 50.2%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Tencent Hy4 preview | 77.1% | Aug 2026 | Model card | |
| 2 | Tencent Hy3 | 50.2% | 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.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 28 Aug 2026 | Tencent Hy4 preview | 77.1 | E-Bench (Internal) |
| 2 Jul 2026 | Tencent Hy3 | 50.2 | e-bench (internal) |
More in Economic work
- JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
- GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate.
Seed2.1 Pro 87.9% - GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
- AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
- CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished).
Qwen3.8-Omni-Flash 75.3% - OfficeQA In use Grounded reasoning over a large corpus of U.S. Treasury Bulletin documents: locate tables and compute precise numeric answers. Claude Opus 4.7 86.3%