Model comparison
Qwen3-Sushi-MathCoder vs o3
Capability radar, value bars, and side-by-side posture.
Qwen3-Sushi-MathCoder
Not scored
value score
o3
93
value score
Qwen3-Sushi-MathCoder ctx
—
o3 ctx
200K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- o393
Attribute tape
| Field | Qwen3-Sushi-MathCoder | o3 |
|---|---|---|
| Developer | kazako5er | OpenAI |
| Context | — | 200K |
| Modalities | Text, Code | |
| Openness | — | Proprietary Model |
| Speed | — | — |
| Price | — | $10/1M in · $40/1M out |
| Value score | — | 93 |
| 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 reasoning model focused on hard problems. |