← All comparisons

Claude 4.5 Haiku (Reasoning) vs Ministral 3 8B

Anthropic vs Mistral — side-by-side benchmark comparison

Claude 4.5 Haiku (Reasoning)Ministral 3 8B
Intelligence Index37.114.8
Coding Index32.610.0
Math Index83.731.7
Output speed (tok/s)142.2100.9
Blended price ($/1M)$2.19$0.15
Time to first token (s)10.48s0.37s
aime
aime 2583.7%31.7%
artificial analysis coding index32.6010.00
artificial analysis intelligence index37.1014.80
artificial analysis math index83.7031.70
gpqa67.2%47.1%
hle9.7%4.3%
ifbench54.3%29.1%
lcr70.3%24.0%
livecodebench61.5%30.3%
math 500
mmlu pro76.0%64.2%
scicode43.3%20.8%
tau254.7%26.6%
terminalbench hard27.3%4.5%

Benchmark data from Artificial Analysis.