SeaEval - Dialogue - SAMSum (Zero-Shot) — leaderboard
Metric: Average ROUGE (0-100). Source: huggingface.co. 25 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 2 2B (IT) | 31.12 |
| 2 | Gemma 2 9B (IT) | 31.01 |
| 3 | Llama 3 8B Cpt Sea Lionv2.1 Instruct | 30.5 |
| 4 | Qwen 2.5 7B Instruct | 29.88 |
| 5 | SeaLLMs-v3-7B-Chat | 29.6 |
| 6 | Llama 3 70B Instruct | 28.94 |
| 7 | Llama 3.1 70B Instruct | 28.93 |
| 8 | Qwen 2.5 72B Instruct | 28.85 |
| 9 | Llama 3 8B Instruct | 28.46 |
| 10 | Qwen 2.5 32B Instruct | 28.44 |
| 11 | Llama 3.1 8B Instruct | 28.21 |
| 12 | Qwen 2 72B Instruct | 28.01 |
| 13 | Qwen 2.5 14B Instruct | 27.14 |
| 14 | Qwen 2.5 3B Instruct | 26.94 |
| 15 | Qwen 2 7B Instruct | 25.67 |
Interactive version: theaggregate.ai/benchmark?slug=seaeval-dialogue-samsum-zero-shot · How the rankings work · Data refreshed daily, snapshot 2026-07-22.