CLAMBER - Zero-shot - Identification F1: leaderboard
Metric: F1 (%). Source: arxiv.org. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-3.5 Turbo 16K | 53.45 |
| 2 | Llama 2 13B Chat | 50.99 |
| 3 | vicuna-13B | 39.97 |
| 4 | Llama 2 70B Chat | 34.27 |
Interactive version: theaggregate.ai/benchmark?slug=clamber-zero-shot-identification-f1 · How It Works · Data refreshed daily, snapshot 2026-09-19.