AdaExploreBench - Exact Accuracy: leaderboard

An agent makes case-by-case decisions (four ordered actions) in finance, healthcare, cybersecurity or manufacturing under a hidden rule it must discover by designing its own probe cases, and the rule changes without announcement partway through the episode (HKUST KnowComp; 256 test episodes, main setting with masked evaluation history). Exact accuracy is the share of evaluation cases where the agent picks the optimal action.

Metric: EA (%) (0-100). Source: hkust-knowcomp.github.io. Saturation forecast: Around February 2027. 7 models tracked. Updated 19 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3.8 FlashHigh69.47#43
2GPT-6 SolHigh65.69#33
3DeepSeek V4.1 FlashHigh58.01#69
4GPT-6 LunaHigh46.5#106
5Qwen 3.8 27BMedium45.95#220
6Gemma 4 12B (IT)High37.98#731
7Qwen 3.5 9B32.17#829

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

Interactive version: theaggregate.ai/benchmark?slug=adaexplorebench-exact-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-20.