DialToM - Retrospective (Persuasion): leaderboard
Metric: Correctness rate (%) on four-option multiple-choice questions of the DialToM Retrospective task: identify a speaker's mental state (belief, desire, intention, emotion, knowledge, trust) from the dialogue context, persuasion domain (naturalistic human-human dialogues from PersuasionForGood; GPT-4o-drafted options verified by professional annotators and Dawid-Skene aggregation), zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 98.78 |
| 2 | Qwen 3 235B A22B | 97.94 |
| 3 | GPT-5 | 95.28 |
| 4 | Gemini 2.5 Pro | 94.99 |
| 5 | Gemini 2.5 Flash | 94.4 |
| 6 | GPT-4.1 | 94.4 |
| 7 | Kimi K2 | 93.22 |
| 8 | Llama 3.3 70B | 87.91 |
| 9 | GPT-OSS-120B | 85.25 |
| 10 | Llama 4 Maverick | 79.28 |
| 11 | Mistral Small 3.2 | 74.34 |
| 12 | Mistral Nemo | 56.64 |
| 13 | Llama 3.1 8B | 34.51 |
Interactive version: theaggregate.ai/benchmark?slug=dialtom-retrospective-persuasion · How It Works · Data refreshed daily, snapshot 2026-10-07.