← All comparisons

Claude 4.5 Haiku (Non-reasoning) vs GLM-4.6 (Non-reasoning)

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

Claude 4.5 Haiku (Non-reasoning)GLM-4.6 (Non-reasoning)
Intelligence Index31.030.2
Coding Index29.630.2
Math Index39.044.3
Output speed (tok/s)105.853.2
Blended price ($/1M)$2.19$1.00
Time to first token (s)0.65s1.84s
aime
aime 2539.0%44.3%
artificial analysis coding index29.6030.20
artificial analysis intelligence index31.0030.20
artificial analysis math index39.0044.30
gpqa64.6%63.2%
hle4.3%5.2%
ifbench42.0%36.7%
lcr43.7%26.3%
livecodebench51.1%56.1%
math 500
mmlu pro80.0%78.4%
scicode34.4%33.1%
tau232.5%76.9%
terminalbench hard27.3%28.8%

Benchmark data from Artificial Analysis.