DialToM - Prospective (Motivational Interviewing): leaderboard

Prospective theory of mind on DialToM (2026), naturalistic human-human dialogues from motivational interviewing sessions (AnnoMI): 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), motivational interviewing domain (naturalistic human-human dialogues from AnnoMI; 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

#ModelScoreOverall rank
1Gemini 3 Pro (Preview)83.09#119
2Gemini 2.5 Pro38.24#276
3Gemini 2.5 Flash26.47#463
4Kimi K222.06#443
5Llama 3.3 70B18.42#1514
6Qwen 3 235B A22B17.65#628
7GPT-514.71#178
8DialToM DeepSeek v3 (checkpoint unspecified)10.29
9Llama 4 Maverick9.56#1110
10GPT-OSS-120B7.35#704
11Llama 3.1 8B6.62#5196
12Mistral Nemo6.62#4484
13GPT-4.15.88#505
14Mistral Small 3.25.88#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-motivational-interviewing · How It Works · Data refreshed daily, snapshot 2026-11-21.