Compare, 2 models
Side by side.
Claude Opus 4.8 and GPT-5.6 Luna 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-5.6 LunaOpenAI |
|---|---|---|
| Lab | Anthropic | OpenAI |
| Type | Language | Language |
| Released | May 28, 2026 | Jul 9, 2026 |
| Input price$ per 1M tokens | $5.00 | $0.20 |
| Output price$ per 1M tokens | $25.00 | $1.20 |
| Blended price3 input tokens per output | $10.00 | $0.45 |
| 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-5.6 LunaOpenAI |
|---|---|---|
| Epoch Capabilities IndexOverall, higher is better | 159 | 157 |
| LMArena textOverall, higher is better | 1481High, style control | 1452xHigh, style control |
| ARC-AGI-2Reasoning and knowledge, higher is better | 72.1%high setting | 59.5%max setting |
| FrontierMath Tiers 1-3Reasoning and knowledge, higher is better | 80.0%max setting | 82.1%max setting |
| GPQA DiamondReasoning and knowledge, higher is better | 91.0%max setting | 91.6%max setting |
n/a means the board has not published a score for that model.