- Intelligence
- 22.2
- Rank 216 of 744 measured models
- Coding
- 45.3
- Rank 137 of 298 measured models
- Output speed
- 37.9 t/s
- Rank 370 of 403 measured models
- Price/1M
- $1
- Rank 379 of 659 measured models
- Context window
- 200K
- Rank 618 of 1199 measured models
GLM-4.7 (Reasoning) scores 22.2 on the Artificial Analysis Intelligence Index, ranking 216th of 744 measured models. The closest models on this index are Grok 4 (22.5), MiMo-V2-Flash (Feb 2026) (22.4), and Gemini 3.5 Flash-Lite (22.2). At $1 per million tokens (3:1 input/output blended price), it is cheaper than Grok 4 ($6), more expensive than Gemini 3.5 Flash-Lite ($0.85). With an output speed of 37.9 t/s, it is slower than Grok 4 (74 t/s) and Gemini 3.5 Flash-Lite (435 t/s).
Additional benchmarks12
Design Arena · 3d54.3%
Design Arena · Androidnative56.1%
Design Arena · Asciiart48.2%
Design Arena · Codecategories54.8%
Design Arena · Dataviz51.2%
Design Arena · Fullstack45.1%
Design Arena · Gamedev55.2%
Design Arena · Godotgamedev35.8%
Design Arena · Mobileapps48.9%
Design Arena · Svg54.3%
Design Arena · Uicomponent51.1%
Design Arena · Website55.3%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Grok 4
SpaceXSI · $6 · 74 t/s
22.5+0.3$674 t/sCompare - MiMo-V2-Flash (Feb 2026)
Xiaomi · — · —
22.4+0.2——Compare - Gemini 3.5 Flash-Lite
Google · $0.85 · 435 t/s
22.2$0.85435 t/sCompare - o3-pro
OpenAI · $35 · —
21.9−0.3$35—Compare
