DialToM - Prospective (Emotional Support): leaderboard
Prospective theory of mind on DialToM (2026), naturalistic human-human dialogues from emotional support conversations (ESConv): the model must forecast which next dialogue trajectory fits a given mental-state profile, without the dialogue context, 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 Prospective task: forecast the state-consistent next dialogue trajectory from an isolated mental-state profile with no dialogue context (the State-Driven Diagnostic Probe), emotional support domain (naturalistic human-human dialogues from ESConv; GPT-4o-drafted options verified by professional annotators and Dawid-Skene aggregation), zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 14 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 80.46 | #119 |
| 2 | Gemini 2.5 Pro | 29.06 | #276 |
| 3 | Qwen 3 235B A22B | 29.06 | #628 |
| 4 | Kimi K2 | 25.62 | #443 |
| 5 | Gemini 2.5 Flash | 25.12 | #463 |
| 6 | Llama 3.3 70B | 19.7 | #1514 |
| 7 | Llama 3.1 8B | 16.75 | #5196 |
| 8 | GPT-5 | 16.26 | #178 |
| 9 | GPT-OSS-120B | 15.76 | #704 |
| 10 | Mistral Nemo | 14.29 | #4484 |
| 11 | GPT-4.1 | 12.81 | #505 |
| 12 | Llama 4 Maverick | 11.82 | #1110 |
| 13 | DialToM DeepSeek v3 (checkpoint unspecified) | 11.82 | |
| 14 | Mistral Small 3.2 | 4.93 | #1641 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=dialtom-prospective-emotional-support · How It Works · Data refreshed daily, snapshot 2026-11-21.