Model comparison
lehrm-no-act vs Claude 4 Sonnet
Capability radar, value bars, and side-by-side posture.
lehrm-no-act
Not scored
value score
Claude 4 Sonnet
91
value score
lehrm-no-act ctx
—
Claude 4 Sonnet ctx
200K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Claude 4 Sonnet91
Attribute tape
| Field | lehrm-no-act | Claude 4 Sonnet |
|---|---|---|
| Developer | Unknown | Anthropic |
| Context | — | 200K |
| Modalities | Text, Code, Image | |
| Openness | — | Proprietary Model |
| Speed | — | Fast |
| Price | — | $3/1M in · $15/1M out |
| Value score | — | 91 |
| Summary | An experimental open-weight text-generation model checkpoint by the 'codewithdark' Hugging Face account, belonging to a latent recurrent-depth LM family that iteratively refines an internal latent state rather than producing explicit chain-of-thought outputs. The '-no-act' suffix suggests an ablation variant (likely removing an activation function) within this research architecture. | Balanced Claude model for coding and agents. |