← All comparisons

Claude 4.5 Haiku (Reasoning) vs GLM-5 (Reasoning)

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

Claude 4.5 Haiku (Reasoning)GLM-5 (Reasoning)
Intelligence Index37.149.8
Coding Index32.644.2
Math Index83.7
Output speed (tok/s)142.275.7
Blended price ($/1M)$2.19$1.55
Time to first token (s)10.48s0.66s
aime
aime 2583.7%
artificial analysis coding index32.6044.20
artificial analysis intelligence index37.1049.80
artificial analysis math index83.70
gpqa67.2%82.0%
hle9.7%27.2%
ifbench54.3%72.3%
lcr70.3%63.3%
livecodebench61.5%
math 500
mmlu pro76.0%
scicode43.3%46.2%
tau254.7%98.2%
terminalbench hard27.3%43.2%

Benchmark data from Artificial Analysis.