SeaEval - Fundamental NLP Tasks - WNLI (Few-Shot): leaderboard
SeaEval few-shot WNLI evaluation measuring core NLP understanding such as inference, acceptability, paraphrase, or reading-comprehension accuracy.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 70B | 73.24 | #592 |
| 2 | Llama 3.1 8B | 57.75 | #1151 |
| 3 | Llama 3 8B | 49.3 | #1242 |
| 4 | Llama 3 8B Cpt Sea Lionv2 Base | 43.66 | #1182 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=seaeval-fundamental-nlp-tasks-wnli-few-shot · How It Works · Data refreshed daily, snapshot 2026-10-20.