Top 10 for everyday chat
Scores from artificialanalysis.ai and lmarena.ai.
API price is per 1M tokens, in / out. Updated Nov 2, 2026.
| # | Model | Artificial Analysis | LMArena text | API price |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 57.6 | 1,516 | $4 / $20 |
| 2 | Gemini 4 Argon | — | — | $2 / $10 |
| 3 | Claude Fable 5.1 | 53.4 | 1,513 | $10 / $50 |
| 4 | Claude Sonnet 5.5 | 56.0 | 1,473 | $2 / $10 |
| 5 | GPT-6 Astra | 52.7 | — | $10 / $50 |
| 6 | Gemini 3.8 Flash | 40.9 | 1,498 | $0.75 / $3.75 |
| 7 | GLM 5.3 | 44.8 | 1,474 | $1.40 / $4.40 |
| 8 | Qwen 3.8 Max | 45.4 | 1,484 | $2 / $6 |
| 9 | Muse Spark 1.3 | 48.1 | 1,491 | $1.25 / $4.25 |
| 10 | Kimi K3 | 43.6 | 1,475 | $3 / $15 |
We rank every model per task, blending public leaderboards with our own blind tests where we have them. Price and speed don’t count toward the rank. How we rank