TAU2
Measured Jul 10, 2026Source
Score
0.27
Models12 0 
Hermes 4 - Llama-3.1 405B (Non-reasoning)
Nous ResearchNous ResearchUnited States
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.
CodingReasoningFastLong context
Input / 1M tokens
$1.00Output / 1M tokens
$3.00Output tokens/s
39.6First-token seconds
0.72sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.1
Lcr
Measured Jul 10, 2026Source
Score
0.2
Ifbench
Measured Jul 10, 2026Source
Score
0.35
Aime 25
Measured Jul 10, 2026Source
Score
0.15
Scicode
Measured Jul 10, 2026Source
Score
0.35
Livecodebench
Measured Jul 10, 2026Source
Score
0.55
Hle
Measured Jul 10, 2026Source
Score
0.04
Gpqa
Measured Jul 10, 2026Source
Score
0.54
Mmlu Pro
Measured Jul 10, 2026Source
Score
0.73
Artificial Analysis Math Index
Measured Jul 10, 2026Source
Score
15.3
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
8.8
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