Model comparison
sft-out vs GPT-5
Capability radar, value bars, and side-by-side posture.
sft-out
Not scored
value score
GPT-5
94
value score
sft-out ctx
—
GPT-5 ctx
400K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- GPT-594
Attribute tape
| Field | sft-out | GPT-5 |
|---|---|---|
| Developer | Nanthasit | OpenAI |
| Context | — | 400K |
| Modalities | Text, Code, Image, Audio | |
| Openness | — | Proprietary Model |
| Speed | — | Fast |
| Price | — | Mid-High |
| Value score | — | 94 |
| 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. | OpenAI frontier multimodal model. |