Nano GPT logo
NanoGPT
Provider logo

Hermes Low

hermes-low
BackTry Model
Provider logo

Hermes Low

hermes-low
BackTry Model

Currently points to Gemini 3.1 Flash Lite. Lowest tier for Hermes-style agent work: lowest cost for routine, fast, high-volume tasks.

Added May 11, 2026

Context Window

1.0M

Max Output

65.5K

Input Price (Auto)

$0.25/1M

Output Price (Auto)

$1.50/1M

Cache Read (Auto)

$0.025/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

25.6

Better than 63% of models compared

Coding Index

34.7

Better than 45% of models compared

Agentic Index

6.5

Better than 27% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

82.2%

Better than 73% of models compared

HLE

Humanity's Last Exam

17.2%

Better than 72% of models compared

IFBench

Instruction-following benchmark

77.2%

Better than 96% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

31.3%

Better than 38% of models compared

AA-LCR

Long context reasoning evaluation

71.3%

Better than 83% of models compared

Coding

SciCode

Python programming for scientific computing

41.9%

Better than 77% of models compared

Terminal-Bench Hard

Agentic coding and terminal use

24.2%

Better than 64% of models compared

Last updated Aug 16, 2026

Artificial Analysis

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…

Compare Hermes Low with similar models from the same provider or model family.

Claw Low

claw-low

Currently points to Gemini 3.1 Flash Lite. Lowest tier for OpenClaw-style agent work: lowest cost for routine, fast, high-volume tasks.

Hermes High

hermes-high

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.

Hermes Medium

hermes-medium

Currently points to MiniMax M2.7. Middle tier for Hermes-style agent work: medium intelligence and cost for capable everyday tool use.

Claw High

claw-high

Currently 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.

Claw Medium

claw-medium

Currently points to MiniMax M2.7. Middle tier for OpenClaw-style agent work: medium intelligence and cost for capable everyday tool use.

Linkup Research Low

linkup-research-low

Linkup Research with low reasoning depth. Runs an async web research agent and returns a sourced answer for factual and multi-source questions. Responses can take several minutes.