Compare, 2 models
Side by side.
GPT-5.4 and Qwen3.8-Max on every board at least two of them share. Blue marks the best in each row.
Specs
List prices, context and published output speed. Blue marks the best in each row.
| Spec | GPT-5.4OpenAI | Qwen3.8-MaxAlibaba |
|---|---|---|
| Lab | OpenAI | Alibaba |
| Type | Language | Language |
| Released | Mar 5, 2026 | Sep 2, 2026 |
| Input price$ per 1M tokens | $2.50 | $2.00 |
| Output price$ per 1M tokens | $15.00 | $6.00 |
| Blended price3 input tokens per output | $5.63 | $3.00 |
| Contexttokens | 1.05M | 1M |
| Open weights | No | No |
| Output speedTok / s | n/a | 40 |
Benchmarks
Every board where at least two of these models have a published score. Each score links to its source.
| Board | GPT-5.4OpenAI | Qwen3.8-MaxAlibaba |
|---|---|---|
| Epoch Capabilities IndexOverall, higher is better | 157 | 157 |
| LMArena textOverall, higher is better | 1475High, style control | 1483style control |
| FrontierMath Tiers 1-3Reasoning and knowledge, higher is better | 78.6%xhigh setting | 74.7%xhigh setting |
| GPQA DiamondReasoning and knowledge, higher is better | 93.3%xhigh setting | 92.7%xhigh setting |
n/a means the board has not published a score for that model.