AttuneBench - Pairwise Accuracy: leaderboard

AttuneBench (2026) scores LLM emotional intelligence on genuine multi-turn conversations whose participants annotated their own emotions, preferred responses and judgments of how the model behaved. This board is the pairwise accuracy (%) with which a model predicts which of three responses per turn the participant preferred, in the default mode on 200 conversations; higher is better.

Metric: Pairwise accuracy (%) at predicting the participant's preferences among three response variants per turn (original, preference-informed alternate, participant-written golden), Default mode (conversation only), 200 conversations; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 4.764.6#86
2Claude Opus 4.663.7#114
3MiMo-V2-Pro59.8#356
4Claude Haiku 4.556#587
5GPT-5.553.8#56
6Mistral Large51.7#2144
7Claude Sonnet 4.651.2#179
8Gemini 3.1 Pro (Preview)50.3#102
9GPT-5.447#138
10Grok 446.1#321
11Qwen 2.5 72B45#1189

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=attunebench-pairwise-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-22.