Anthropic: Claude Opus 4.8 wins on more metrics (6 of 8), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Anthropic: Claude Opus 4.8 | OpenAI: GPT-5.5 |
|---|---|---|
| Intelligence Index | 61.4✓ | 56.7 |
| Coding Index | 56.7✓ | 56.2 |
| GPQA Diamond | 92% | 93%✓ |
| Design Arena Elo | 1372✓ | 1354 |
| Speed (tokens/sec) | 59✓ | 36 |
| Latency | 1.8s✓ | 2.8s |
| Input price /M | $5.00 | $5.00 |
| Output price /M | $25.00✓ | $30.00 |
| Context window | 1M | 1.1M✓ |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSONVision |