OpenAI: GPT-5.3-Codex wins on more metrics (5 of 8), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Anthropic: Claude Sonnet 4.6 | OpenAI: GPT-5.3-Codex |
|---|---|---|
| Intelligence Index | 42.6 | 53.6✓ |
| Coding Index | 43.0 | 53.1✓ |
| GPQA Diamond | 80% | 92%✓ |
| Design Arena Elo | 1329✓ | 1230 |
| Speed (tokens/sec) | 44 | 44 |
| Latency | 1.3s✓ | 4.2s |
| Input price /M | $3.00 | $1.75✓ |
| Output price /M | $15.00 | $14.00✓ |
| Context window | 1M✓ | 400K |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSONVision |