TAU2
Measured Jul 10, 2026Source
Score
0.23
Models12 0 
Hermes 4 - Llama-3.1 70B (Reasoning)
Nous ResearchNous ResearchUnited States
Hermes 4 is a fine-tuned version of Llama-3.1 70B, specifically optimized for enhanced reasoning and chain-of-thought capabilities. It excels at complex problem-solving, logical deduction, and following intricate instructions, making it suitable for tasks requiring deep analysis. As part of the Hermes series, it maintains strong tool-use and coding proficiency.
ReasoningCoding
Input / 1M tokens
$0.13Output / 1M tokens
$0.40Output tokens/s
87.12First-token seconds
0.57sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.05
Lcr
Measured Jul 10, 2026Source
Score
0.07
Ifbench
Measured Jul 10, 2026Source
Score
0.31
Aime 25
Measured Jul 10, 2026Source
Score
0.69
Scicode
Measured Jul 10, 2026Source
Score
0.34
Livecodebench
Measured Jul 10, 2026Source
Score
0.65
Hle
Measured Jul 10, 2026Source
Score
0.08
Gpqa
Measured Jul 10, 2026Source
Score
0.7
Mmlu Pro
Measured Jul 10, 2026Source
Score
0.81
Artificial Analysis Math Index
Measured Jul 10, 2026Source
Score
68.7
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
10
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server