Compare, 2 models
Side by side.
GPT-5.4 and GPT-5.5 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.
Benchmarks
Every board where at least two of these models have a published score. Each score links to its source.
| Board | GPT-5.4OpenAI | GPT-5.5OpenAI |
|---|---|---|
| Epoch Capabilities IndexOverall, higher is better | 157 | 160 |
| LMArena textOverall, higher is better | 1475High, style control | 1482High, style control |
| ARC-AGI-2Reasoning and knowledge, higher is better | 74.0%xhigh setting | 85.0%xhigh setting |
| FrontierMath Tiers 1-3Reasoning and knowledge, higher is better | 78.6%xhigh setting | 85.3%xhigh setting |
| GPQA DiamondReasoning and knowledge, higher is better | 93.3%xhigh setting | 94.0%xhigh setting |
n/a means the board has not published a score for that model.