- Intelligence
- 43.4
- Rank 46 of 744 measured models
- Output speed
- 236 t/s
- Rank 23 of 403 measured models
- Price/1M
- $0.20
- Rank 161 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $0.213
- Rank 74 of 193 measured models
Claude Haiku 5.5 (Max) scores 43.4 on the Artificial Analysis Intelligence Index, ranking 46th of 744 measured models. The closest models on this index are Grok 4.6 (44.3), Step 5 Preview (43.7), and Kimi K3 (43.6). At $0.20 per million tokens (3:1 input/output blended price), it is cheaper than Grok 4.6 ($3), Step 5 Preview ($1.43), and Kimi K3 ($6). With an output speed of 236 t/s, it is faster than Grok 4.6 (50 t/s), Step 5 Preview (89.3 t/s), and Kimi K3 (43.3 t/s).
Additional benchmarks6
Design Arena · 3d59.3%
Design Arena · Codecategories50.0%
Design Arena · Dataviz55.3%
Design Arena · Gamedev53.6%
Design Arena · Uicomponent52.9%
Design Arena · Website48.6%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Grok 4.6
SpaceXSI · $3 · 50 t/s
44.3+0.9$350 t/sCompare - Step 5 Preview
StepFun · $1.43 · 89.3 t/s
43.7+0.3$1.4389.3 t/sCompare - Kimi K3
Moonshot AI · $6 · 43.3 t/s
43.6+0.2$643.3 t/sCompare - GPT-5.6 Terra
OpenAI · $4.50 · 107 t/s
42.1−1.3$4.50107 t/sCompare
