- Intelligence
- 44.3
- Rank 40 of 744 measured models
- Coding
- 76.8
- Rank 12 of 298 measured models
- Output speed
- 50 t/s
- Rank 320 of 403 measured models
- Price/1M
- $3
- Rank 487 of 659 measured models
- Context window
- 500K
- Rank 349 of 1199 measured models
- Cost per task
- $1.48
- Rank 150 of 193 measured models
Grok 4.6 (High) scores 44.3 on the Artificial Analysis Intelligence Index, ranking 40th of 744 measured models. The closest models on this index are GLM-5.3 (44.8), Step 5 Preview (43.7), and Kimi K3 (43.6). At $3 per million tokens (3:1 input/output blended price), it is cheaper than Kimi K3 ($6), more expensive than GLM-5.3 ($2.15) and Step 5 Preview ($1.43). With an output speed of 50 t/s, it is faster than Kimi K3 (43.3 t/s), slower than GLM-5.3 (61.1 t/s) and Step 5 Preview (89.3 t/s).
Additional benchmarks16
Design Arena · 3d52.4%
Design Arena · Agenticgamedev47.1%
Design Arena · Androidnative61.4%
Design Arena · Asciiart58.3%
Design Arena · Codecategories52.5%
Design Arena · Dataviz51.4%
Design Arena · Fullstack54.9%
Design Arena · Gamedev54.2%
Design Arena · Godotgamedev53.0%
Design Arena · Htmlslides60.1%
Design Arena · Mobileapps55.7%
Design Arena · Python Pptxslides52.7%
Design Arena · Svg49.0%
Design Arena · Uicomponent53.1%
Design Arena · Webapps56.0%
Design Arena · Website52.2%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GLM-5.3
Z.AI · $2.15 · 61.1 t/s
44.8+0.5$2.1561.1 t/sCompare - Step 5 Preview
StepFun · $1.43 · 89.3 t/s
43.7−0.6$1.4389.3 t/sCompare - Kimi K3
Moonshot AI · $6 · 43.3 t/s
43.6−0.7$643.3 t/sCompare - Claude Haiku 5.5
Anthropic · $0.20 · 236 t/s
43.4−0.9$0.20236 t/sCompare
