Compare, 2 models
Side by side.
Claude Opus 4.8 and GPT-5.4 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 | Claude Opus 4.8Anthropic | GPT-5.4OpenAI |
|---|---|---|
| Lab | Anthropic | OpenAI |
| Type | Language | Language |
| Released | May 28, 2026 | Mar 5, 2026 |
| Input price$ per 1M tokens | $5.00 | $2.50 |
| Output price$ per 1M tokens | $25.00 | $15.00 |
| Blended price3 input tokens per output | $10.00 | $5.63 |
| Contexttokens | 1M | 1.05M |
| Open weights | No | No |
Benchmarks
Every board where at least two of these models have a published score. Each score links to its source.
| Board | Claude Opus 4.8Anthropic | GPT-5.4OpenAI |
|---|---|---|
| Epoch Capabilities IndexOverall, higher is better | 159 | 157 |
| LMArena textOverall, higher is better | 1481High, style control | 1475High, style control |
| ARC-AGI-2Reasoning and knowledge, higher is better | 72.1%high setting | 74.0%xhigh setting |
| FrontierMath Tiers 1-3Reasoning and knowledge, higher is better | 80.0%max setting | 78.6%xhigh setting |
| GPQA DiamondReasoning and knowledge, higher is better | 91.0%max setting | 93.3%xhigh setting |
n/a means the board has not published a score for that model.