Independent model data
AI Model Comparison
Compare leading AI models side by side across benchmarks, price, context window, speed, latency, modality, and license.
Choose two models
Select a model type, then build a side-by-side comparison.
vs
At a glance
How current flagship models compare
A consistent view of benchmark quality, token pricing, context, observed API performance, modality, and license. Missing live measurements are left blank rather than estimated.
| Model | GPQA | Input / output | Context | Speed | TTFT | Modality | License |
|---|---|---|---|---|---|---|---|
| GPT-5.6 SolOpenAI | 94.6% | $5.00/$30.00 | 1.05M | 89 c/s | 4.8s | Text + vision | Proprietary |
| Claude Opus 4.7Anthropic | 94.2% | $5.00/$25.00 | 1M | 125 c/s | 2.6s | Text + vision | Proprietary |
| Gemini 3.1 ProGoogle | 94.3% | $2.50/$15.00 | 1.05M | 148 c/s | 8.9s | Text + vision | Proprietary |
| Grok 4.5xAI | 93.0% | $2.00/$6.00 | 500K | — | — | Text + vision | Proprietary |
