← All comparisons

Qwen3.5 0.8B (Reasoning) vs GPT-5.4 (Non-reasoning)

Alibaba vs OpenAI — side-by-side benchmark comparison

Qwen3.5 0.8B (Reasoning)GPT-5.4 (Non-reasoning)
Intelligence Index10.535.4
Coding Index0.041.0
Math Index
Output speed (tok/s)0.070.9
Blended price ($/1M)$0.02$5.63
Time to first token (s)0.00s0.60s
aime
aime 25
artificial analysis coding index0.0%41.00
artificial analysis intelligence index10.5035.40
artificial analysis math index
gpqa11.1%74.8%
hle1.2%10.6%
ifbench21.5%48.4%
lcr5.3%47.3%
livecodebench
math 500
mmlu pro
scicode0.0%47.1%
tau247.7%35.1%
terminalbench hard0.0%37.9%

Benchmark data from Artificial Analysis.