OpenAI: GPT-5.1-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 Opus 4.5 | OpenAI: GPT-5.1-Codex |
|---|---|---|
| Intelligence Index | 43.1 | 43.1 |
| Coding Index | 42.9✓ | 36.6 |
| GPQA Diamond | 81% | 86%✓ |
| Design Arena Elo | 1297✓ | 1218 |
| Speed (tokens/sec) | 44 | 83✓ |
| Latency | 735ms✓ | 2.6s |
| Input price /M | $5.00 | $1.25✓ |
| Output price /M | $25.00 | $10.00✓ |
| Context window | 200K | 400K✓ |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSONVision |