AMI-ME - Topic Segmentation: leaderboard
Metric: WindowDiff segmentation error (0-1) of the model's topic boundaries against the AMI-ME reference fine-grained segmentation (130 AMI Corpus meetings); lower is better. Source: arxiv.org. Saturation forecast: Not forecast. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek R1 Distill Llama 70B | 0.37 |
| 2 | Qwen 3 32B | 0.37 |
| 3 | Qwen 3 32B (Non-reasoning) | 0.38 |
| 4 | GPT-4o | 0.4 |
| 5 | Llama 3.3 70B Instruct | 0.41 |
| 6 | Gemini 2.5 Flash (Non-reasoning) | 0.45 |
Interactive version: theaggregate.ai/benchmark?slug=ami-me-topic-segmentation · How It Works · Data refreshed daily, snapshot 2026-10-07.