← All comparisons

GPT-5.4 mini (xhigh) vs Qwen3 VL 235B A22B (Reasoning)

OpenAI vs Alibaba — side-by-side benchmark comparison

GPT-5.4 mini (xhigh)Qwen3 VL 235B A22B (Reasoning)
Intelligence Index48.927.6
Coding Index51.520.9
Math Index88.3
Output speed (tok/s)182.835.6
Blended price ($/1M)$1.69$2.17
Time to first token (s)4.25s5.14s
aime
aime 2588.3%
artificial analysis coding index51.5020.90
artificial analysis intelligence index48.9027.60
artificial analysis math index88.30
gpqa87.5%77.2%
hle26.6%10.1%
ifbench73.3%56.5%
lcr69.3%58.7%
livecodebench64.6%
math 500
mmlu pro83.6%
scicode49.9%39.9%
tau283.3%54.1%
terminalbench hard52.3%11.4%

Benchmark data from Artificial Analysis.