← All comparisons

GLM-5.1 (Reasoning) vs Claude 4.1 Opus (Reasoning)

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

GLM-5.1 (Reasoning)Claude 4.1 Opus (Reasoning)
Intelligence Index51.442.0
Coding Index43.436.5
Math Index80.3
Output speed (tok/s)61.244.5
Blended price ($/1M)$2.15$32.81
Time to first token (s)0.86s8.55s
aime
aime 2580.3%
artificial analysis coding index43.4036.50
artificial analysis intelligence index51.4042.00
artificial analysis math index80.30
gpqa86.8%80.9%
hle28.0%11.9%
ifbench76.3%55.4%
lcr62.3%66.3%
livecodebench65.4%
math 500
mmlu pro88.0%
scicode43.8%40.9%
tau297.7%71.4%
terminalbench hard43.2%34.3%

Benchmark data from Artificial Analysis.