Decision tool
Which model?
Three choices, five picks — ranked from the same verified data as the rest of the terminal, with the scoring rule in plain sight. No quiz, no black box.
300 candidate models · verified Jun 15, 2026 · methodology
For
Optimize
Limits
| # | Pick | Cap | $/1M | tok/s | |
|---|---|---|---|---|---|
| 1 | Gemini 3.1 Pro PreviewGoogle | 97.9 | $4.5 | 142 | quality leader |
| 2 | GPT-5.5OpenAI | 97.3 | $11.25 | 78 | −0.6 pts vs best |
| 3 | Qwen3.7 MaxAlibabaopen | 96.1 | $3.75 | 199 | −1.8 pts vs best |
| 4 | Kimi K2.6Kimiopen | 96.0 | $1.71 | 46 | −1.9 pts vs best |
| 5 | MiMo-V2.5-ProXiaomi | 95.5 | $0.544 | 43 | −2.4 pts vs best |
Compare top 3 →
Quality = cross-benchmark capability. Budget/Fastest pick among models within 15 pts of the best. Balanced = quality − 8·log₁₀(price) + 3·log₁₀(speed). Same data as everywhere on Modelyst — sources on every model page.
Want the full picture instead? The frontier shows every model on the capability-price plane, and the cost calculator prices your exact workload.