Compare Models
A metric-by-metric comparison using the latest available benchmark, runtime, and pricing values. Gemini 4 Argon (High) wins more comparable metrics.
| Metric | Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback) | Gemini 4 Argon (High) |
|---|---|---|
| Artificial Analysis Intelligence Index | 57.6 | 52.6 |
| LiveBench Mathematics | 97.1% | n/a |
| Humanity's Last Exam | 61.4% | 57.1% |
| SciCode | 66.9% | 61.8% |
| Output Speed | 95.9 tok/s | n/a |
| Time to First Token | 479.92 s | n/a |
| Blended Price | $8.00 / 1M | $4.00 / 1M |
| Input Price | $4.00 / 1M | $2.00 / 1M |
| Output Price | $20.00 / 1M | $10.00 / 1M |
| Value Index | 7.2 | 13.15 |
