← All comparisons

Mistral Medium 3.5 vs Claude 4.1 Opus (Reasoning)

Mistral vs Anthropic — side-by-side benchmark comparison

Mistral Medium 3.5Claude 4.1 Opus (Reasoning)
Intelligence Index39.242.0
Coding Index35.436.5
Math Index80.3
Output speed (tok/s)169.944.5
Blended price ($/1M)$3.00$32.81
Time to first token (s)0.52s8.55s
aime
aime 2580.3%
artificial analysis coding index35.4036.50
artificial analysis intelligence index39.2042.00
artificial analysis math index80.30
gpqa74.8%80.9%
hle12.8%11.9%
ifbench68.8%55.4%
lcr61.0%66.3%
livecodebench65.4%
math 500
mmlu pro88.0%
scicode39.6%40.9%
tau294.2%71.4%
terminalbench hard33.3%34.3%

Benchmark data from Artificial Analysis.