Inception: Mercury 2 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 | Inception: Mercury 2 |
|---|---|---|
| Intelligence Index | 33.0✓ | 32.8 |
| Coding Index | 30.6 | 30.6 |
| GPQA Diamond | 68% | 77%✓ |
| Design Arena Elo | 1220✓ | — |
| Speed (tokens/sec) | 50 | 476✓ |
| Latency | 720ms | 253ms✓ |
| Input price /M | $3.00 | $0.250✓ |
| Output price /M | $15.00 | $0.750✓ |
| Context window | 1M✓ | 128K |
| Capabilities | ReasoningToolsVision | ReasoningToolsJSON |