Anthropic: Claude Opus 4.7 wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Anthropic: Claude Opus 4.7 | OpenAI: GPT-5.3-Codex |
|---|---|---|
| Intelligence Index | 57.3✓ | 53.6 |
| Coding Index | 52.5 | 53.1✓ |
| GPQA Diamond | 91% | 92%✓ |
| Design Arena Elo | 1503✓ | 1229 |
| Speed (tokens/sec) | 63✓ | 53 |
| Latency | 1.6s✓ | 4.2s |
| Input price /M | $5.00 | $1.75✓ |
| Output price /M | $25.00 | $14.00✓ |
| Context window | 1M✓ | 400K |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSONVision |