HumanLikeness - Meaning-1 — leaderboard
Metric: Humanlike Score (%). Source: huggingface.co. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 70B Instruct | 80.22 |
| 2 | Llama 3.1 8B Instruct | 79 |
| 3 | Phi-3 Mini 4K Instruct | 76.07 |
| 4 | Llama 2 13B Chat Base | 73.9 |
| 5 | GPT-3.5 Turbo | 71.44 |
| 6 | c4ai-command-r-plus | 65.64 |
| 7 | starchat2-15B-v0.1 | 62.24 |
| 8 | Yi 1.5 34B Chat | 60.87 |
| 9 | Llama 3 8B Instruct | 58.94 |
| 10 | CodeLlama-34B-Instruct-hf | 58.04 |
| 11 | Llama 3 70B Instruct | 56.57 |
| 12 | Mistral Nemo Instruct (2407) | 51.53 |
| 13 | Llama 2 7B Chat | 50.31 |
| 14 | Mistral 7B Instruct (v0.3) | 49.23 |
| 15 | GPT-4o | 47.21 |
Interactive version: theaggregate.ai/benchmark?slug=humanlikeness-meaning-1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.