DialToM - Retrospective (Persuasion): leaderboard
Retrospective theory of mind on DialToM (2026), naturalistic human-human dialogues from persuasion dialogues (PersuasionForGood): the model must identify the mental state (belief, desire, intention, emotion, knowledge or trust) of a speaker from the dialogue so far, choosing among four annotator-verified options. Correctness rate in percent; higher is better.
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. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DialToM DeepSeek v3 (checkpoint unspecified) | 98.82 | |
| 2 | Gemini 3 Pro (Preview) | 98.78 | #119 |
| 3 | Qwen 3 235B A22B | 97.94 | #628 |
| 4 | GPT-5 | 95.28 | #178 |
| 5 | Gemini 2.5 Pro | 94.99 | #276 |
| 6 | Gemini 2.5 Flash | 94.4 | #463 |
| 7 | GPT-4.1 | 94.4 | #505 |
| 8 | Kimi K2 | 93.22 | #443 |
| 9 | Llama 3.3 70B | 87.91 | #1514 |
| 10 | GPT-OSS-120B | 85.25 | #704 |
| 11 | Llama 4 Maverick | 79.28 | #1110 |
| 12 | Mistral Small 3.2 | 74.34 | #1641 |
| 13 | Mistral Nemo | 56.64 | #4484 |
| 14 | Llama 3.1 8B | 34.51 | #5196 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=dialtom-retrospective-persuasion · How It Works · Data refreshed daily, snapshot 2026-11-21.