Drift-Bench (State-Oriented, With Clarification) - Intention: leaderboard

Metric: Success rate (%; 200 AgentBench operating-system and database tasks with an intention fault (the stated goal changed), clarification tools answered by a persona user simulator, mean of 3 trials). Source: arxiv.org. Saturation forecast: Around 2029. 7 models tracked.

Top models

#ModelScore
1Qwen 3 235B A22B 2507 Instruct66.67
2Llama 4 Maverick59.33
3GPT-5.255.9
4Gemini 2.5 Flash55.33
5DeepSeek V3.255.33
6GLM-4.752.17
7GPT-OSS-120B50.49

Interactive version: theaggregate.ai/benchmark?slug=drift-bench-state-oriented-with-clarification-intention · How It Works · Data refreshed daily, snapshot 2026-09-25.