← All comparisons

Claude 4.5 Haiku (Non-reasoning) vs Ministral 3 14B

Anthropic vs Mistral — side-by-side benchmark comparison

Claude 4.5 Haiku (Non-reasoning)Ministral 3 14B
Intelligence Index31.016.0
Coding Index29.610.9
Math Index39.030.0
Output speed (tok/s)105.890.6
Blended price ($/1M)$2.19$0.20
Time to first token (s)0.65s0.37s
aime
aime 2539.0%30.0%
artificial analysis coding index29.6010.90
artificial analysis intelligence index31.0016.00
artificial analysis math index39.0030.00
gpqa64.6%57.2%
hle4.3%4.6%
ifbench42.0%32.0%
lcr43.7%22.0%
livecodebench51.1%35.1%
math 500
mmlu pro80.0%69.3%
scicode34.4%23.6%
tau232.5%27.2%
terminalbench hard27.3%4.5%

Benchmark data from Artificial Analysis.