TAU2
Measured May 14, 2026Source
Score
0.22
Models13 0 
Nous Research
Hermes 4 - Llama-3.1 70B (Non-reasoning)
Nous ResearchNous ResearchUnited States
Hermes 4 is a 70B parameter model from the Hermes series, fine-tuned on Llama-3.1. It is optimized for strong tool use and instruction following, making it suitable for general-purpose dialogue and task execution without a specialized reasoning focus.
CodingLong context
Input / 1M tokens
$0.13Output / 1M tokens
$0.40Output tokens/s
81.04First-token seconds
0.61sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0
Lcr
Measured May 14, 2026Source
Score
0.02
Ifbench
Measured May 14, 2026Source
Score
0.29
Aime 25
Measured May 14, 2026Source
Score
0.11
Scicode
Measured May 14, 2026Source
Score
0.28
Livecodebench
Measured May 14, 2026Source
Score
0.27
Hle
Measured May 14, 2026Source
Score
0.04
Gpqa
Measured May 14, 2026Source
Score
0.49
Mmlu Pro
Measured May 14, 2026Source
Score
0.66
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
11.3
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
9.2
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
12.6
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
Discussion
Thinking... Make sure you are connected to GitHub server