Text2DistBench - Most Frequent: leaderboard

Text2DistBench (2026) tests distributional reading comprehension: given viewer comments on newly released movies and songs, a model reports how opinions are distributed over topics and sentiments rather than single facts. This board is accuracy from 0 to 1 at naming the most frequent topic or sentiment value, averaged over marginal, conditional and joint questions; higher is better.

Metric: Accuracy (fraction) of naming the most frequent topic or sentiment value in the comments, averaged over marginal, conditional and joint questions; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 6 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5.10.839#240
2Grok 4 Fast0.805#447
3Gemini 2.5 Pro0.804#276
4Llama 3.3 70B0.755#1514
5Claude Sonnet 4.50.751#261
6Qwen 3 32B0.673#972

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=text2distbench-most-frequent · How It Works · Data refreshed daily, snapshot 2026-11-21.