Anthropic: Claude Opus 4.8 wins on more metrics (7 of 9), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Anthropic: Claude Opus 4.8 | OpenAI: GPT-5.3-Codex |
|---|---|---|
| Intelligence Index | 61.4✓ | 53.6 |
| Coding Index | 56.7✓ | 53.1 |
| GPQA Diamond | 92%✓ | 92% |
| Design Arena Elo | 1372✓ | 1229 |
| Speed (tokens/sec) | 59✓ | 53 |
| Latency | 1.8s✓ | 4.2s |
| Input price /M | $5.00 | $1.75✓ |
| Output price /M | $25.00 | $14.00✓ |
| Context window | 1M✓ | 400K |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSONVision |