- Intelligence
- 11.1
- Rank 400 of 744 measured models
- Output speed
- 71.1 t/s
- Rank 248 of 403 measured models
- Price/1M
- $0.372
- Rank 226 of 659 measured models
- Context window
- 128K
- Rank 773 of 1199 measured models
GLM-4.5-Air scores 11.1 on the Artificial Analysis Intelligence Index, ranking 400th of 744 measured models. The closest models on this index are Granite 4.2 8B (11.1), Grok 4 Fast (11.1), and Ling 3.0 Tiny (11.1). At $0.372 per million tokens (3:1 input/output blended price), it is more expensive than Granite 4.2 8B ($0.107) and Grok 4 Fast ($0.275). With an output speed of 71.1 t/s, it is faster than Ling 3.0 Tiny (16.5 t/s), slower than Granite 4.2 8B (114 t/s).
Additional benchmarks7
Design Arena · 3d54.1%
Design Arena · Codecategories51.4%
Design Arena · Dataviz58.5%
Design Arena · Gamedev48.4%
Design Arena · Svg50.8%
Design Arena · Uicomponent54.4%
Design Arena · Website51.3%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Qwen3 Next 80B A3B
Alibaba · $0.412 · 163 t/s
11.2+0.1$0.412163 t/sCompare - Granite 4.2 8B
IBM · $0.107 · 114 t/s
11.1$0.107114 t/sCompare - Grok 4 Fast
SpaceXSI · $0.275 · —
11.1$0.275—Compare - Ling 3.0 Tiny
InclusionAI · — · 16.5 t/s
11.1—16.5 t/sCompare
