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
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Flash (High) | 38.3 |
| 2 | Claude Sonnet 4.6 | 35 |
| 3 | GPT-5.4 (Medium) | 35 |
| 4 | DeepSeek V4 Flash (Max) | 35 |
| 5 | DeepSeek V4 Flash (Non-reasoning) | 33.3 |
| 6 | GPT-5.4 (Non-reasoning) | 28.3 |
| 7 | GPT-5 Mini | 25 |
| 8 | Gemini 2.5 Flash | 13.8 |
| 9 | Qwen 3 32B | 11.7 |
Interactive version: theaggregate.ai/benchmark?slug=tau-rec-pass-pow-4 · How It Works · Data refreshed daily, snapshot 2026-09-29.