tau-Rec - Pass^4: leaderboard

Metric: pass^4 (0-1 scaled to %), the probability that the agent succeeds on all four independent trials of a task under the strict constraint and policy check; the agent recommends one movie from a 153-title TMDB catalog to a GPT-5 mini user simulator through dialogue and catalog tools on 60 tasks (constraints revealed up front, only on asking, or never), 4 trials per task, agent temperature 0 where supported; higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 9 models tracked.

Top models

#ModelScore
1DeepSeek V4 Flash (High)38.3
2Claude Sonnet 4.635
3GPT-5.4 (Medium)35
4DeepSeek V4 Flash (Max)35
5DeepSeek V4 Flash (Non-reasoning)33.3
6GPT-5.4 (Non-reasoning)28.3
7GPT-5 Mini25
8Gemini 2.5 Flash13.8
9Qwen 3 32B11.7

Interactive version: theaggregate.ai/benchmark?slug=tau-rec-pass-pow-4 · How It Works · Data refreshed daily, snapshot 2026-09-29.