AdaExploreBench - Change Recognition: leaderboard
AdaExploreBench's auxiliary check of whether the agent noticed what changed when its hidden decision rule drifted mid-episode: the rule change is split into atomic changes and the agent's before-and-after answers are scored against them (main setting, 256 episodes).
Metric: Change Rec. (%) (0-100). Source: hkust-knowcomp.github.io. Saturation forecast: Around February 2027. 7 models tracked. Updated 19 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3.8 Flash | High | 63.68 | #43 |
| 2 | GPT-6 Sol | High | 47.56 | #33 |
| 3 | DeepSeek V4.1 Flash | High | 44.52 | #69 |
| 4 | Qwen 3.8 27B | Medium | 25.93 | #220 |
| 5 | Qwen 3.5 9B | 13.8 | #829 | |
| 6 | Gemma 4 12B (IT) | High | 10.34 | #731 |
| 7 | GPT-6 Luna | High | 9.96 | #106 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=adaexplorebench-change-recognition · How It Works · Data refreshed daily, snapshot 2026-11-20.