Private AI
Hermes 4 70B with thinking enabled. Emits explicit reasoning content before final answer when streamed.
Added Sep 17, 2025
Model weightsContext Window
128.0K
Max Output
8.2K
Input Price (Auto)
$0.20/1M
Output Price (Auto)
$0.40/1M
Cache Read (Auto)
$0.10/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
10.0
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
69.9%
Better than 52% of models compared
HLE
Humanity's Last Exam
7.9%
Better than 54% of models compared
IFBench
Instruction-following benchmark
31.3%
Better than 16% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
22.5%
Better than 24% of models compared
AA-LCR
Long context reasoning evaluation
6.7%
Better than 18% of models compared
CritPt
Research-level physics reasoning
0.0%
SciCode
Python programming for scientific computing
34.1%
Better than 51% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
4.5%
AIME 2025
American Invitational Mathematics Examination 2025
68.7%
Better than 64% of models compared
MMLU-Pro
Professional and academic subject knowledge
81.1%
Better than 73% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
23.3%
Last updated Aug 4, 2026
Artificial AnalysisBetter than 29% of models compared
LiveCodeBench
Contamination-free coding benchmark
65.3%
Better than 72% of models compared
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
95.4%
