Hermes 4 - Llama-3.1 405B (Reasoning)
Nous ResearchLlama
Release Date
2025-08-27
Parameters
—
Context Length
—
Modalities
—
Capability Radar
31
general
59
coding
70
reasoning
44
scienceest.
80
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 243 | 40.0 | AA |
| General Ranking | 316 | 34.0 | AA |
| Math Reasoning | 120 | 70.0 | AA |
| Science | 238 | 45.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
50.5%SR
Code
HumanEval
88.4%SR
Finance
MMLU
86.0%SR
MMLU-Pro
68.9%SR
General
IFEval
92.1%SR
MBPP EvalPlus
87.6%SR
BFCL v2
77.3%SR
Math
MGSM
91.1%SR
MATH
77.0%SR
AA Evaluation Indices
Math Index69.7
Intelligence Index9.0
Mmlu Pro0.8
Gpqa0.7
Aime 250.7
Livecodebench0.7
Ifbench0.3
Scicode0.3
Tau20.2
Lcr0.2
Terminalbench Hard0.1
Hle0.1
LLM Stats Category Scores
Instruction Following90
Structured Output90
Code90
Language80
Legal80
Math80
Reasoning80
Finance80
Healthcare80
Tool Calling80
General70
Physics50
Biology50
Chemistry50
Pricing
Input Price$1 / 1M tokens
Output Price$3 / 1M tokens
Blended Price (3:1)$1.5 / 1M tokens
Speed
Tokens/sec39.9
Time to First Token0.85s
Time to Answer50.94s
Provider Price Ranking
Provider Price Ranking
1 providers
ProviderInputOutput
1Nous ResearchPRIMARY
$1
$3
Compare pricing across different API providers for this model.