HumanLikeness - Syntax-1 — leaderboard
Metric: Humanlike Score (%). Source: huggingface.co. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Phi-3 Mini 4K Instruct | 89.36 |
| 2 | starchat2-15B-v0.1 | 86.93 |
| 3 | zephyr-7B-alpha | 84.56 |
| 4 | Mistral Nemo Instruct (2407) | 84.21 |
| 5 | Llama 3.1 8B Instruct | 83.58 |
| 6 | CodeLlama-34B-Instruct-hf | 82.34 |
| 7 | Llama 3.1 70B Instruct | 81.26 |
| 8 | Llama 3 8B Instruct | 78.94 |
| 9 | GPT-3.5 Turbo | 76.33 |
| 10 | Llama 2 13B Chat Base | 74.98 |
| 11 | Mistral 7B Instruct (v0.3) | 74.89 |
| 12 | c4ai-command-r-plus | 72.36 |
| 13 | Mistral 7B Instruct (v0.2) | 72.27 |
| 14 | Yi 1.5 34B Chat | 72.24 |
| 15 | zephyr-7B-beta | 71.37 |
Interactive version: theaggregate.ai/benchmark?slug=humanlikeness-syntax-1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.