Model comparison
sft-out vs Claude 4 Sonnet
Capability radar, value bars, and side-by-side posture.
sft-out
Not scored
value score
Claude 4 Sonnet
91
value score
sft-out ctx
—
Claude 4 Sonnet ctx
200K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Claude 4 Sonnet91
Attribute tape
| Field | sft-out | Claude 4 Sonnet |
|---|---|---|
| Developer | Nanthasit | Anthropic |
| Context | — | 200K |
| Modalities | Text, Code, Image | |
| Openness | — | Proprietary Model |
| Speed | — | Fast |
| Price | — | $3/1M in · $15/1M out |
| Value score | — | 91 |
| Summary | A supervised fine-tuned model checkpoint by Nanthasit (Nanthasit Burankum), built on Qwen2.5-0.5B-Instruct and designed for lightweight Thai-language chat and text completion at sub-1B parameter scale. Intended as a base for further SFT or PEFT adaptation rather than a production-grade high-capability model. | Balanced Claude model for coding and agents. |