TAU2
Measured May 14, 2026Source
Score
0.22
Models13 0 
Nous Research
Hermes 4 - Llama-3.1 405B (Reasoning)
Nous ResearchNous ResearchUnited States
Hermes 4 is Nous Research's latest flagship model, fine-tuned from Meta's Llama-3.1 405B. It is specifically optimized for complex reasoning tasks, offering strong instruction-following and conversational capabilities.
ReasoningCoding
Input / 1M tokens
$1.00Output / 1M tokens
$3.00Output tokens/s
35.13First-token seconds
0.87sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.11
Lcr
Measured May 14, 2026Source
Score
0.21
Ifbench
Measured May 14, 2026Source
Score
0.33
Aime 25
Measured May 14, 2026Source
Score
0.7
Scicode
Measured May 14, 2026Source
Score
0.25
Livecodebench
Measured May 14, 2026Source
Score
0.69
Hle
Measured May 14, 2026Source
Score
0.1
Gpqa
Measured May 14, 2026Source
Score
0.73
Mmlu Pro
Measured May 14, 2026Source
Score
0.83
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
69.7
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
16
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
18.6
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