Hermes 4 Llama 3.1 405B is Nous Research's language model. A 405B-parameter Llama 3.1-based hybrid reasoning LLM from Nous Research with selectable deliberate thinking or direct response modes.
Specifications
Canonical IDnousresearch-hermes-4-llama-3-1-405b
TypeLanguage
StatusActive
CreatorNous ResearchNous Research
Input ModalitiesText
Output ModalitiesText
Parameters405B
Benchmarks
Intelligence Index
17.6
#252
Coding Index
18.1
#194
Math Index
15.3
#209
MMLU-Pro
0.7
#183
GPQA
0.5
#293
HLE
0.0
#371
LiveCodeBench
0.5
#123
IFBench
0.3
#275
Time to First Token
0.74s
#297
SciCode
0.3
#177
AIME 2025
0.2
#209
LCR
0.2
#245
TerminalBench Hard
0.1
#196
TAU2
0.3
#247
Output TPS
35.4
#246

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama 3.3 70B Instruct131K$0.100$0.200Available
Llama 3.2 3B Instruct131K$0.015$0.020Deprecated
Llama 3.2 1B Instruct131K$0.027$0.080Deprecated
Llama 3.1 405B Instruct131K$0.120$0.300Deprecating
Llama 3.1 70B Instruct131K$0.100$0.100Available
Llama 3.1 8B Instruct200K$0.020$0.030Available
Llama 3.1 70B128K$0.600$0.600Available
Llama 3.1 8B131K$0.030$0.050Available
Llama 3 70B Instruct131K$0.120$0.300Available
Llama 3 8B Instruct32K$0.030$0.040Available
Hermes 4 Llama 3.1 405BCurrent

Model IDs