Anthropic: Claude Fable 5 vs OpenAI: GPT-5.2-Codex
Anthropic: Claude Fable 5 wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Anthropic: Claude Fable 5 | OpenAI: GPT-5.2-Codex |
|---|---|---|
| Intelligence Index | 59.9✓ | 40.1 |
| Coding Index | 76.5✓ | — |
| GPQA Diamond | 93%✓ | 90% |
| Design Arena Elo | 1381✓ | — |
| Speed (tokens/sec) | 54 | 64✓ |
| Latency | 4.2s | 1.6s✓ |
| Input price /M | $10.00 | $1.75✓ |
| Output price /M | $50.00 | $14.00✓ |
| Context window | 1M✓ | 400K |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSONVision |