Benchmark Almanac

E-Bench-Code (Tencent)

GPT-5.6 Sol 83.3% leads since August 2026
In use

Agents complete Tencent in-house work tasks that need code. Task and scoring details are not published.

Made by
Tencent Hy team
Released
August 2026
Kind
Documents and spreadsheets
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
Kept private
Strongest model tested
Claude Opus 5 #10 on the capability index
Last in a launch post
August 2026
Last model added
August 2026
Scores refreshed
November 12th, 2026
8
Models scored on its own leaderboard
1
Launch post lists it, from 1 lab

GPT-5.6 Sol leads with 83.3% among models released by August 2026

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in August 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 83.3 GPT-5.6 Sol
  2. 82.7 Claude Opus 5
  3. 79.0 Tencent Hy4 preview
  4. 77.6 Kimi K3
  5. 67.1 Qwen 3.8 Max
  6. 66.5 GLM-5.3
  7. 64.4 Tencent Hy3
  8. 64.3 DeepSeek V4 Pro 0813
  1. 1 GPT-5.6 Sol highest available reasoning 83.3%
  2. 2 Claude Opus 5 highest available reasoning 82.7%
  3. 3 Tencent Hy4 preview highest available reasoning 79%
  4. 4 Kimi K3 highest available reasoning 77.6%
  5. 5 Qwen 3.8 Max highest available reasoning 67.1%
  6. 6 GLM-5.3 highest available reasoning 66.5%
  7. 7 Tencent Hy3 highest available reasoning 64.4%
  8. 8 DeepSeek V4 Pro 0813 highest available reasoning 64.3%

Source: Official E-Bench-Code (Tencent) leaderboard

#ModelScoreSettingDateSource
1 GPT-5.6 Sol 83.3% highest available reasoning Jul 2026 Official leaderboard
2 Claude Opus 5 82.7% highest available reasoning Jul 2026 Official leaderboard
3 Tencent Hy4 preview 79% highest available reasoning Aug 2026 Official leaderboard
4 Kimi K3 77.6% highest available reasoning Jul 2026 Official leaderboard
5 Qwen 3.8 Max 67.1% highest available reasoning Aug 2026 Official leaderboard
6 GLM-5.3 66.5% highest available reasoning Aug 2026 Official leaderboard
7 Tencent Hy3 64.4% highest available reasoning Jul 2026 Official leaderboard
8 DeepSeek V4 Pro 0813 64.3% highest available reasoning Aug 2026 Official leaderboard

Labs report scores for 1 model in their cards. We plot every source in the charts below.

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard Not tested since Aug 2026
GPT-5.6 Sol 83.3%

Source: Official E-Bench-Code (Tencent) leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-5.6 Sol Tencent Hy3 0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-5.6 Sol Tencent Hy3

Sources: Official E-Bench-Code (Tencent) leaderboard and labs’ model cards

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
DateLaunch postScoreAs the post writes it
Aug 28, 2026 Tencent Hy4 preview 79 E-Bench-Code (Internal)

One lab claim next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.

Model Lab says Board says Gap
Tencent Hy4 preview 79% E-Bench-Code (Internal) 79% Leaderboard, highest available reasoning Same

More in Economic work

All 97 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). Claude Fable 5 75.9%
  • 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%