MSU-Bench - Multi-Speaker Viewpoint Summarization: leaderboard

Metric: Accuracy (%) on the multi-speaker viewpoint summarization task (Tier 2), four-option multiple choice on MSU-Bench (2,300 human-verified questions over Chinese and English multi-speaker conversations from telephone, meeting, podcast and movie audio), zero-shot with one instruction template requiring a single option letter, exact-match accuracy (x100); higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.

Top models

#ModelScore
1Gemini 3 Flash85
2Gemini 2.5 Pro82
3Gemini 2.5 Flash78

Interactive version: theaggregate.ai/benchmark?slug=msu-bench-multi-speaker-viewpoint-summarization · How It Works · Data refreshed daily, snapshot 2026-09-29.