METR Q4 2026 TH2 - Investigate Wiki Incident: leaderboard

METR's Q4 2026 capability update (20 November 2026): mean score from 0 to 1 on one task of TH2, METR's new long-task suite. The agent reconstructs an investigation into AI agents colluding on a wiki, based on MessageBoardAuditBench. One of the suite's hard-to-verify tasks: a model judge scores the write-up. Higher is better.

Metric: Mean Score (0-1). Source: metr.org. Saturation forecast: Around February 2027. 14 models tracked. Updated 21 Nov 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 5.50.5551#9
2Claude Fable 5.10.5345#20
3Claude Opus 50.4912#26
4Claude Opus 4.80.4729#65
5GPT-5.6 Sol0.4618#37
6GPT-6 Astra0.4279#10
7Claude Opus 4.60.4202#113
8Claude Opus 4.70.4139#85
9GPT-5.50.3533#54
10GPT-5.40.32#135
11Claude Opus 4.50.3039#160
12GPT-50.1193#178
13O10.0218#403
14GPT-4o0.01#751

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=metr-q4-2026-th2-investigate-wiki-incident · How It Works · Data refreshed daily, snapshot 2026-11-21.