HumanLikeness - Syntax-2 — leaderboard
Metric: Humanlike Score (%). Source: huggingface.co. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3 8B Instruct | 79.49 |
| 2 | Llama 3.1 8B Instruct | 79.21 |
| 3 | Llama 3.1 70B Instruct | 78.42 |
| 4 | GPT-4o | 78.35 |
| 5 | Mistral Nemo Instruct (2407) | 77.18 |
| 6 | GPT-3.5 Turbo | 77.07 |
| 7 | GPT-4o Mini | 76.94 |
| 8 | Llama 3 70B Instruct | 76.72 |
| 9 | starchat2-15B-v0.1 | 73.32 |
| 10 | c4ai-command-r-plus | 72.4 |
| 11 | Yi 1.5 34B Chat | 70.6 |
| 12 | Phi-3 Mini 4K Instruct | 69.29 |
| 13 | Llama 2 7B Chat | 67.19 |
| 14 | Llama 2 13B Chat Base | 65.18 |
| 15 | Mistral 7B Instruct (v0.2) | 58.71 |
Interactive version: theaggregate.ai/benchmark?slug=humanlikeness-syntax-2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.