← All comparisons

Qwen3.5 4B (Non-reasoning) vs GPT-5 (medium)

Alibaba vs OpenAI — side-by-side benchmark comparison

Qwen3.5 4B (Non-reasoning)GPT-5 (medium)
Intelligence Index22.642.0
Coding Index13.738.9
Math Index91.7
Output speed (tok/s)210.086.4
Blended price ($/1M)$0.06$3.44
Time to first token (s)0.23s37.15s
aime91.7%
aime 2591.7%
artificial analysis coding index13.7038.90
artificial analysis intelligence index22.6042.00
artificial analysis math index91.70
gpqa71.2%84.2%
hle7.5%23.5%
ifbench33.3%70.6%
lcr28.3%72.8%
livecodebench70.3%
math 50099.1%
mmlu pro86.7%
scicode18.3%41.1%
tau287.7%86.5%
terminalbench hard11.4%37.9%

Benchmark data from Artificial Analysis.