SeaEval - Fundamental NLP Tasks - MRPC (Zero-Shot) — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2 72B Instruct | 80.64 |
| 2 | Qwen 2.5 72B Instruct | 80.15 |
| 3 | Qwen 2 7B Instruct | 78.68 |
| 4 | Qwen 2.5 14B Instruct | 77.94 |
| 5 | Sailor2-8B-Chat | 77.7 |
| 6 | Qwen 2.5 32B Instruct | 77.45 |
| 7 | Llama 3.1 70B Instruct | 76.96 |
| 8 | Llama 3 70B Instruct | 75.98 |
| 9 | SeaLLMs-v3-7B-Chat | 74.75 |
| 10 | Gemma 2 9B (IT) | 74.02 |
| 11 | Gemma 2 2B (IT) | 70.83 |
| 12 | Qwen 2.5 7B Instruct | 70.59 |
| 13 | Qwen 2.5 1.5B Instruct | 68.38 |
| 14 | Llama 3 8B Instruct | 67.89 |
| 15 | Llama 3.1 8B Instruct | 66.67 |
Interactive version: theaggregate.ai/benchmark?slug=seaeval-fundamental-nlp-tasks-mrpc-zero-shot · How the rankings work · Data refreshed daily, snapshot 2026-07-22.