HumanLikeness - Discourse-1 — leaderboard
Metric: Humanlike Score (%). Source: huggingface.co. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Phi-3 Mini 4K Instruct | 79.7 |
| 2 | Llama 3.1 70B Instruct | 79.69 |
| 3 | Llama 3.1 8B Instruct | 79.26 |
| 4 | CodeLlama-34B-Instruct-hf | 79.12 |
| 5 | Mistral Nemo Instruct (2407) | 78.61 |
| 6 | Yi 1.5 34B Chat | 77.91 |
| 7 | c4ai-command-r-plus | 77.7 |
| 8 | Llama 3 8B Instruct | 77.02 |
| 9 | zephyr-7B-alpha | 76.23 |
| 10 | GPT-3.5 Turbo | 76.07 |
| 11 | Llama 2 13B Chat Base | 75.97 |
| 12 | Llama 3 70B Instruct | 75.54 |
| 13 | Llama 2 7B Chat | 75.48 |
| 14 | GPT-4o | 75.43 |
| 15 | starchat2-15B-v0.1 | 75.11 |
Interactive version: theaggregate.ai/benchmark?slug=humanlikeness-discourse-1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.