GroupToM-Bench - Desire: leaderboard

Metric: strict exact-match accuracy (%) over multi-select options (random 6.7) on Level 2 desire inference (latent psychological motives behind stated goals), multiple choice; 240 multimodal multi-agent scenarios (scene image plus dialogue); higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 11 models tracked.

Top models

#ModelScore
1Gemini 3 Pro77.1
2GPT-4o75.3
3GPT-574.1
4Claude Haiku 4.573.2
5GPT-5 Mini70.3
6GPT-5 Nano64.8
7InternVL3.5-8B60.7
8Qwen 2.5 VL 7B Instruct58.2
9Qwen 2 VL 7B54.9

Interactive version: theaggregate.ai/benchmark?slug=grouptom-bench-desire · How It Works · Data refreshed daily, snapshot 2026-09-29.