Qwen: Qwen3.7 Max wins on more metrics (7 of 9), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | OpenAI: GPT-5.3-Codex | Qwen: Qwen3.7 Max |
|---|---|---|
| Intelligence Index | 53.6 | 56.6✓ |
| Coding Index | 53.1✓ | 50.1 |
| GPQA Diamond | 92% | 92%✓ |
| Design Arena Elo | 1229 | 1331✓ |
| Speed (tokens/sec) | 53✓ | 45 |
| Latency | 4.2s | 1.6s✓ |
| Input price /M | $1.75 | $1.25✓ |
| Output price /M | $14.00 | $3.75✓ |
| Context window | 400K | 1M✓ |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSON |