← All comparisons

Claude 4.5 Haiku (Non-reasoning) vs GLM-4.5V (Non-reasoning)

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

Claude 4.5 Haiku (Non-reasoning)GLM-4.5V (Non-reasoning)
Intelligence Index31.012.7
Coding Index29.610.8
Math Index39.015.3
Output speed (tok/s)105.822.6
Blended price ($/1M)$2.19$0.90
Time to first token (s)0.65s49.70s
aime
aime 2539.0%15.3%
artificial analysis coding index29.6010.80
artificial analysis intelligence index31.0012.70
artificial analysis math index39.0015.30
gpqa64.6%57.3%
hle4.3%3.6%
ifbench42.0%28.6%
lcr43.7%0.0%
livecodebench51.1%35.2%
math 500
mmlu pro80.0%75.1%
scicode34.4%18.8%
tau232.5%19.6%
terminalbench hard27.3%6.8%

Benchmark data from Artificial Analysis.