← All comparisons

Claude 4.1 Opus (Non-reasoning) vs Mistral Small 3

Anthropic vs Mistral — side-by-side benchmark comparison

Claude 4.1 Opus (Non-reasoning)Mistral Small 3
Intelligence Index36.012.7
Coding Index
Math Index4.3
Output speed (tok/s)44.7150.2
Blended price ($/1M)$32.81$0.10
Time to first token (s)1.63s0.48s
aime8.0%
aime 254.3%
artificial analysis coding index
artificial analysis intelligence index36.0012.70
artificial analysis math index4.30
gpqa46.2%
hle4.1%
ifbench26.4%
lcr0.0%
livecodebench25.2%
math 50071.5%
mmlu pro65.2%
scicode23.6%
tau219.6%
terminalbench hard

Benchmark data from Artificial Analysis.