TAU2
Measured May 14, 2026Source
Score
0.27
Nous Research
Hermes 4 is a large language model from Nous Research, fine-tuned on the Llama-3.1 405B base. This 'Non-reasoning' variant is optimized for direct, high-quality instruction following and conversational tasks without an extended chain-of-thought process. It leverages the scale of the 405B parameter model for strong general performance.
Benchmark history
Score
0.27
Score
0.1
Score
0.2
Score
0.35
Score
0.15
Score
0.35
Score
0.55
Score
0.04
Score
0.54
Score
0.73
Score
15.3
Score
18.1
Score
17.6
Plan availability

Thinking... Make sure you are connected to GitHub server