- Intelligence
- 24.7
- Rank 179 of 744 measured models
- Coding
- 63.0
- Rank 74 of 298 measured models
- Output speed
- 45.2 t/s
- Rank 335 of 403 measured models
- Price/1M
- $6
- Rank 587 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
Claude Sonnet 4.6 (Non-reasoning, High) scores 24.7 on the Artificial Analysis Intelligence Index, ranking 179th of 744 measured models. The closest models on this index are GPT-5.1 (24.7), Solar Open2 250B (24.7), and Ling-3.0-flash-VL (24.6). At $6 per million tokens (3:1 input/output blended price), it is more expensive than GPT-5.1 ($3.44) and Ling-3.0-flash-VL ($0.111). With an output speed of 45.2 t/s, it is slower than GPT-5.1 (112 t/s) and Ling-3.0-flash-VL (124 t/s).
Additional benchmarks14
Design Arena · 3d57.6%
Design Arena · Agenticgamedev52.2%
Design Arena · Androidnative62.0%
Design Arena · Asciiart60.1%
Design Arena · Codecategories59.4%
Design Arena · Dataviz58.2%
Design Arena · Fullstack64.3%
Design Arena · Gamedev58.8%
Design Arena · Godotgamedev60.6%
Design Arena · Mobileapps63.6%
Design Arena · Svg58.7%
Design Arena · Uicomponent58.3%
Design Arena · Webapps57.0%
Design Arena · Website60.0%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-5 Codex (High)
OpenAI · $3.44 · 166 t/s
24.9+0.2$3.44166 t/sCompare - GPT-5.1
OpenAI · $3.44 · 112 t/s
24.7$3.44112 t/sCompare - Solar Open2 250B
Upstage · — · —
24.7——Compare - Ling-3.0-flash-VL
InclusionAI · $0.111 · 124 t/s
24.6−0.1$0.111124 t/sCompare
