HumanLikeness - Meaning-2 — leaderboard
Metric: Humanlike Score (%). Source: huggingface.co. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Nemo Instruct (2407) | 75.1 |
| 2 | Llama 3.1 8B Instruct | 73.74 |
| 3 | zephyr-7B-alpha | 73.13 |
| 4 | zephyr-7B-beta | 72.93 |
| 5 | Llama 2 13B Chat Base | 71.65 |
| 6 | Llama 3.1 70B Instruct | 66.52 |
| 7 | Llama 3 8B Instruct | 65.66 |
| 8 | Yi 1.5 34B Chat | 64.86 |
| 9 | Mistral 7B Instruct (v0.2) | 64.02 |
| 10 | CodeLlama-34B-Instruct-hf | 63.11 |
| 11 | GPT-4o | 60.82 |
| 12 | Llama 2 7B Chat | 60.09 |
| 13 | c4ai-command-r-plus | 59.23 |
| 14 | Mixtral 8x7B Instruct (v0.1) | 59.03 |
| 15 | Llama 3 70B Instruct | 58.91 |
Interactive version: theaggregate.ai/benchmark?slug=humanlikeness-meaning-2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.