Benchmark Almanac

Honor of Kings Bug AI Root Cause Analysis

Not in model cards

Agents use the Honor of Kings Bug AI platform to identify the cause of code defects. The team measures how often agents identify the correct cause.

Tencent reports that root cause accuracy rose from 59.5% to 73.8% in the Hy4 release. The team gives no case count.

Released
November 2026
Kind
Tasks from real jobs
Level
University
Answers
Agent task
Tasks
Kept private
Measures
Capability
In and out
Text, Code → Actions, Text
Interaction
Agentic
Environment
Honor of Kings Bug AI
Refresh
One fixed set
Last model added
November 2026
Scores refreshed
November 21st, 2026
2
Models scored on its own leaderboard

Tencent Hy4 leads with 73.8%

Best score per model from the benchmark's own leaderboard, read on November 21st, 2026. Where a model ran with several settings or harnesses, we keep its best.

  1. 1 Tencent Hy4 73.8%
  2. 2 Tencent Hy4 preview 59.5%

Source: Official Honor of Kings Bug AI Root Cause Analysis leaderboard

#ModelScoreSettingDateSource
1 Tencent Hy4 73.8% Nov 2026 Official leaderboard
2 Tencent Hy4 preview 59.5% Aug 2026 Official 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 Best so far
0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Tencent Hy4 Tencent Hy4 preview 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Tencent Hy4 Tencent Hy4 preview

Source: Official Honor of Kings Bug AI Root Cause Analysis leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Economic work

All 210 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
  • Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
  • 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%

Data audit

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (2 entries).
  • Note Models scored Only 2 models we track.
  • Pass Newest score The newest is from November 2026, for Tencent Hy4.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 73.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on hunyuan.tencent.com: 2 rows for models we track at the last read.
  • Pass Last read November 21st, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check