TriggerBench - PM Accuracy: leaderboard
Metric: PM accuracy (%) over all 1,265 tasks (positive clean, positive overloaded and negative clean variants); base dialogues of about 2.5K tokens; TriggerBench: 1,265 prospective-memory tasks from 488 dialogue blueprints in five dimensions (state tracking, temporal grounding, logical adherence, attention recovery, safe coding); a constraint is stated early in a dialogue and a later trigger turn calls for acting on it without being asked; GPT-4o (T=0) judges whether the reply fulfils the proactive intent; temperature 0.6; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (High) | 83.24 |
| 2 | GPT-5.2 (Medium) | 81.74 |
| 3 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 74.86 |
| 4 | Gemma 3 27B (IT) | 70.59 |
| 5 | GPT-5.2 (Non-reasoning) | 69.33 |
| 6 | GPT-4.1 | 60 |
| 7 | Qwen 3 235B A22B 2507 Instruct | 56.21 |
| 8 | GPT-4o | 51.78 |
| 9 | Qwen 3 32B | 40.71 |
Interactive version: theaggregate.ai/benchmark?slug=triggerbench-pm-accuracy · How It Works · Data refreshed daily, snapshot 2026-09-29.