← All comparisons

GPT-5.4 nano (Non-Reasoning) vs Ministral 3 14B

OpenAI vs Mistral — side-by-side benchmark comparison

GPT-5.4 nano (Non-Reasoning)Ministral 3 14B
Intelligence Index24.416.0
Coding Index27.910.9
Math Index30.0
Output speed (tok/s)157.490.6
Blended price ($/1M)$0.46$0.20
Time to first token (s)0.54s0.37s
aime
aime 2530.0%
artificial analysis coding index27.9010.90
artificial analysis intelligence index24.4016.00
artificial analysis math index30.00
gpqa55.8%57.2%
hle4.2%4.6%
ifbench32.7%32.0%
lcr24.7%22.0%
livecodebench35.1%
math 500
mmlu pro69.3%
scicode35.2%23.6%
tau234.8%27.2%
terminalbench hard24.2%4.5%

Benchmark data from Artificial Analysis.