Currently points to Claude 4.7 Opus. Highest tier for Hermes-style agent work: most expensive, strongest intelligence, and best suited for hard multi-step tasks.
Added May 11, 2026
Context Window
1.0M
Max Output
128.0K
Input Price (Auto)
$5.00/1M
Output Price (Auto)
$25.00/1M
Cache Read (Auto)
$2.50/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
43.9
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
88.5%
Better than 88% of models compared
HLE
Humanity's Last Exam
33.3%
Better than 88% of models compared
IFBench
Instruction-following benchmark
43.6%
Better than 48% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
74.0%
Better than 66% of models compared
AA-LCR
Long context reasoning evaluation
72.3%
Better than 84% of models compared
CritPt
Research-level physics reasoning
5.1%
Coding
SciCode
Python programming for scientific computing
50.1%
Better than 91% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
54.5%
Better than 97% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
44.7%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
54.1%
Last updated Aug 16, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Hermes High with similar models from the same provider or model family.
Claw High
claw-highCurrently points to Claude 4.7 Opus. Highest tier for OpenClaw-style agent work: most expensive, strongest intelligence, and best suited for hard multi-step tasks.
Hermes Low
hermes-lowCurrently points to Gemini 3.1 Flash Lite. Lowest tier for Hermes-style agent work: lowest cost for routine, fast, high-volume tasks.
Hermes Medium
hermes-mediumCurrently points to MiniMax M2.7. Middle tier for Hermes-style agent work: medium intelligence and cost for capable everyday tool use.
Claw Low
claw-lowCurrently points to Gemini 3.1 Flash Lite. Lowest tier for OpenClaw-style agent work: lowest cost for routine, fast, high-volume tasks.
Claw Medium
claw-mediumCurrently points to MiniMax M2.7. Middle tier for OpenClaw-style agent work: medium intelligence and cost for capable everyday tool use.
Kimi K2.7 Code High-Speed
moonshotai/kimi-k2.7-code-highspeedKimi K2.7 Code High-Speed is the accelerated coding-focused variant tuned for fast agentic software engineering. It targets roughly 180 tokens per second, with short-context responses reaching up to about 260 tokens per second for rapid coding iterations.