HumanLikeness - Sound-1 — leaderboard
Metric: Humanlike Score (%). Source: huggingface.co. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 70B Instruct | 88.51 |
| 2 | c4ai-command-r-plus | 79.19 |
| 3 | CodeLlama-34B-Instruct-hf | 78.53 |
| 4 | Mistral Nemo Instruct (2407) | 74.09 |
| 5 | Llama 2 7B Chat | 73.76 |
| 6 | Llama 3.1 8B Instruct | 73.14 |
| 7 | Llama 3 8B Instruct | 68.62 |
| 8 | Yi 1.5 34B Chat | 66.54 |
| 9 | Phi-3 Mini 4K Instruct | 60.76 |
| 10 | Mixtral 8x7B Instruct (v0.1) | 59.96 |
| 11 | Llama 3 70B Instruct | 59.94 |
| 12 | GPT-4o | 59.56 |
| 13 | starchat2-15B-v0.1 | 58.11 |
| 14 | Llama 2 13B Chat Base | 56.71 |
| 15 | zephyr-7B-alpha | 56.6 |
Interactive version: theaggregate.ai/benchmark?slug=humanlikeness-sound-1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.