OpenAI: gpt-oss-120b wins on more metrics (6 of 9), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Anthropic: Claude Sonnet 4 | OpenAI: gpt-oss-120b |
|---|---|---|
| Intelligence Index | 33.0 | 33.3✓ |
| Coding Index | 30.6✓ | 28.6 |
| GPQA Diamond | 68% | 78%✓ |
| Design Arena Elo | 1220✓ | 1062 |
| Speed (tokens/sec) | 50 | 554✓ |
| Latency | 720ms | 161ms✓ |
| Input price /M | $3.00 | $0.039✓ |
| Output price /M | $15.00 | $0.180✓ |
| Context window | 1M✓ | 131K |
| Capabilities | ReasoningToolsVision | ReasoningToolsJSON |