- Intelligence
- 41.8
- Rank 54 of 744 measured models
- Coding
- 71.5
- Rank 46 of 298 measured models
- Output speed
- 64.5 t/s
- Rank 271 of 403 measured models
- Price/1M
- $0.237
- Rank 182 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $0.284
- Rank 83 of 193 measured models
GLM-5.3-Flash scores 41.8 on the Artificial Analysis Intelligence Index, ranking 54th of 744 measured models. The closest models on this index are GPT-5.6 Terra (42.1), Claude Opus 4.8 (batch) (41.8), and Ling 3.1 Flash (41.1). At $0.237 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.6 Terra ($4.50) and Ling 3.1 Flash ($0.45). With an output speed of 64.5 t/s, it is slower than GPT-5.6 Terra (121 t/s) and Ling 3.1 Flash (213 t/s).
Additional benchmarks8
Design Arena · 3d56.3%
Design Arena · Asciiart54.9%
Design Arena · Codecategories49.4%
Design Arena · Dataviz50.5%
Design Arena · Gamedev47.3%
Design Arena · Svg56.9%
Design Arena · Uicomponent54.9%
Design Arena · Website48.5%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-5.6 Terra
OpenAI · $4.50 · 121 t/s
42.1+0.3$4.50121 t/sCompare - Claude Opus 4.8 (batch)
Anthropic · — · —
41.8——Compare - Ling 3.1 Flash
InclusionAI · $0.45 · 213 t/s
41.1−0.7$0.45213 t/sCompare - Gemini 3.8 Flash
Google · $1.50 · 145 t/s
40.9−0.9$1.50145 t/sCompare
