Linguini: leaderboard
Metric: Exact Match (%; 0 in-context examples, 894 questions). Source: arxiv.org. Saturation forecast: Estimated already saturated. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3 Opus (20240229) | 24.05 |
| 2 | GPT-4o (2024-05-13) | 14.65 |
| 3 | Claude 3 Sonnet (20240229) | 12.3 |
| 4 | GPT-4 Turbo | 8.72 |
| 5 | Llama 3 70B | 8.17 |
| 6 | GPT-4 Preview (0125) | 6.38 |
| 7 | Claude 3 Haiku (20240307) | 6.04 |
| 8 | Llama 3 70B Instruct | 4.81 |
| 9 | Llama 2 70B Base | 4.7 |
| 10 | Mixtral 8x7B (v0.1) | 2.46 |
| 11 | Qwen 1.5 110B Chat | 1.45 |
| 12 | Llama 2 70B Chat (HF) | 0.89 |
| 13 | gemma-2B | 0.34 |
Interactive version: theaggregate.ai/benchmark?slug=linguini · How It Works · Data refreshed daily, snapshot 2026-09-24.