← All comparisons

Claude 4.1 Opus (Reasoning) vs GLM-4.6 (Non-reasoning)

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

Claude 4.1 Opus (Reasoning)GLM-4.6 (Non-reasoning)
Intelligence Index42.030.2
Coding Index36.530.2
Math Index80.344.3
Output speed (tok/s)44.553.2
Blended price ($/1M)$32.81$1.00
Time to first token (s)8.55s1.84s
aime
aime 2580.3%44.3%
artificial analysis coding index36.5030.20
artificial analysis intelligence index42.0030.20
artificial analysis math index80.3044.30
gpqa80.9%63.2%
hle11.9%5.2%
ifbench55.4%36.7%
lcr66.3%26.3%
livecodebench65.4%56.1%
math 500
mmlu pro88.0%78.4%
scicode40.9%33.1%
tau271.4%76.9%
terminalbench hard34.3%28.8%

Benchmark data from Artificial Analysis.