SmophyAI

Published daily · Next update 02:00 UTC

Model family · 14 versions tracked

GLM: every version compared

Z.ai: GLM 5.3 (batch) currently leads the GLM family with an Artificial Analysis Intelligence Index of 44.8. For the best value within the family, Z.ai: GLM 5.3 Flash (batch) costs $0.24/1M tokens blended.

  1. Z.ai: GLM 5.3 (batch) - 44.8 intelligence · $1.29/1M
  2. Z.ai: GLM 5.3 Flash (batch) - 41.8 intelligence · $0.24/1M
  3. Z.ai: GLM 4.7 - 34.5 intelligence · $0.74/1M
  4. Z.ai: GLM 5.2 (free) - 33.7 intelligence · $1.00/1M
  5. Z.ai: GLM 4.6 - 29.3 intelligence · $0.45/1M
  6. Z.ai: GLM 5.1 - 26.1 intelligence · $1.48/1M
  7. Z.ai: GLM 4.7 Flash - - intelligence · $0.15/1M
  8. Z.ai: GLM 5 - - intelligence · $0.93/1M
  9. Z.ai: GLM 5V Turbo - - intelligence · $1.90/1M
  10. Z.ai: GLM 5 Turbo - - intelligence · $1.90/1M
  11. Z.ai: GLM 4.5V - - intelligence · $0.90/1M
  12. Z.ai: GLM 4.5 - - intelligence · $1.00/1M
  13. Z.ai: GLM 4.5 Air - - intelligence · $0.31/1M
  14. Z.ai: GLM 5.3 FlashX - - intelligence · $0.59/1M
All 14 GLM versions, by quality
#ModelIntelligence indexPrice/1M blended
01Z.ai: GLM 5.3 (batch)44.8$1.29
02Z.ai: GLM 5.3 Flash (batch)41.8$0.24
03Z.ai: GLM 4.734.5$0.74
04Z.ai: GLM 5.2 (free)33.7$1.00
05Z.ai: GLM 4.629.3$0.45
06Z.ai: GLM 5.126.1$1.48
07Z.ai: GLM 4.7 Flash-$0.15
08Z.ai: GLM 5-$0.93
09Z.ai: GLM 5V Turbo-$1.90
10Z.ai: GLM 5 Turbo-$1.90
11Z.ai: GLM 4.5V-$0.90
12Z.ai: GLM 4.5-$1.00
13Z.ai: GLM 4.5 Air-$0.31
14Z.ai: GLM 5.3 FlashX-$0.59

GLM real usage share, over time

26.7%20.0%13.3%6.7%0.0%Share of usageJul 5Aug 13Sep 22

Ranked by current quality, not release date - this pipeline's data collection started recently, so "first tracked" timestamps don't reflect true historical release dates yet. The usage-share chart above is real, unaffected by that limitation.

Frequently asked questions

What is the best GLM model?

Z.ai: GLM 5.3 (batch) currently leads the GLM family with an Artificial Analysis Intelligence Index of 44.8.

How much real usage does GLM get?

GLM models account for 18.6% of real OpenRouter token volume as of the latest data.