Anthropic
Claude Sonnet 5
ReasoningClosed weights
- Intelligence
- 28.1
- Rank 143 of 744 measured models
- Output speed
- 57.4 t/s
- Rank 292 of 403 measured models
- Price/1M
- $4
- Rank 532 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $0.999
- Rank 128 of 193 measured models
Claude Sonnet 5 (Medium) scores 28.1 on the Artificial Analysis Intelligence Index, ranking 143rd of 744 measured models. The closest models on this index are Nex-N2-Pro (Based on Qwen3.5-397B-A17B) (28.2), Solar Pro 4 (28.2), and Gemini 3 Pro Preview (28.0). At $4 per million tokens (3:1 input/output blended price), it is cheaper than Gemini 3 Pro Preview ($4.50), more expensive than Solar Pro 4 ($0.525). With an output speed of 57.4 t/s, it is slower than Solar Pro 4 (94.3 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Nex-N2-Pro (Based on Qwen3.5-397B-A17B)
Nex AGI · — · —
28.2+0.1——Compare - Solar Pro 4
Upstage · $0.525 · 94.3 t/s
28.2+0.1$0.52594.3 t/sCompare - Gemini 3 Pro Preview
Google · $4.50 · —
28.0−0.1$4.50—Compare - GLM-5
Z.AI · $1.55 · 70.8 t/s
27.9−0.2$1.5570.8 t/sCompare
