← All comparisons

GLM-4.5V (Reasoning) vs Qwen3 235B A22B 2507 Instruct

Z AI vs Alibaba — side-by-side benchmark comparison

GLM-4.5V (Reasoning)Qwen3 235B A22B 2507 Instruct
Intelligence Index15.125.0
Coding Index10.922.1
Math Index73.071.7
Output speed (tok/s)21.357.0
Blended price ($/1M)$0.90$0.36
Time to first token (s)1.13s1.34s
aime71.7%
aime 2573.0%71.7%
artificial analysis coding index10.9022.10
artificial analysis intelligence index15.1025.00
artificial analysis math index73.0071.70
gpqa68.4%75.3%
hle5.9%10.6%
ifbench34.2%46.1%
lcr0.0%31.2%
livecodebench60.4%52.4%
math 50098.0%
mmlu pro78.8%82.8%
scicode22.1%36.0%
tau222.5%33.3%
terminalbench hard5.3%15.2%

Benchmark data from Artificial Analysis.