Model comparison
Qwen3-Sushi-MathCoder vs GPT-5
Capability radar, value bars, and side-by-side posture.
Qwen3-Sushi-MathCoder
Not scored
value score
GPT-5
94
value score
Qwen3-Sushi-MathCoder ctx
—
GPT-5 ctx
400K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- GPT-594
Attribute tape
| Field | Qwen3-Sushi-MathCoder | GPT-5 |
|---|---|---|
| Developer | kazako5er | OpenAI |
| Context | — | 400K |
| Modalities | Text, Code, Image, Audio | |
| Openness | — | Proprietary Model |
| Speed | — | Fast |
| Price | — | Mid-High |
| Value score | — | 94 |
| Summary | A community fine-tuned model derived from the Qwen3 family, optimized for coding and mathematical reasoning tasks. Published on Hugging Face by the individual account kazako5er, it is a custom adaptation rather than an official Qwen or Alibaba Cloud release. | OpenAI frontier multimodal model. |