Compare Models
A metric-by-metric comparison using the latest available benchmark, runtime, and pricing values. Tie wins more comparable metrics.
| Metric | GPT-5.6 Sol (max) | Kimi K3 (max) |
|---|---|---|
| Artificial Analysis Intelligence Index | 58.9 | 57.1 |
| Artificial Analysis Coding Index | 77.4 | 76.2 |
| LiveBench Mathematics | 96.2% | 84.4% |
| GPQA | 94.1% | 93.5% |
| Humanity's Last Exam | 47.2% | 44.3% |
| SciCode | 56.1% | 58.7% |
| Output Speed | 77 tok/s | 34.5 tok/s |
| Time to First Token | 60.18 s | 2.94 s |
| Blended Price | $11.25 / 1M | $6.00 / 1M |
| Input Price | $5.00 / 1M | $3.00 / 1M |
| Output Price |
| $30.00 / 1M |
| $15.00 / 1M |
| Value Index | 5.24 | 9.52 |
