← All comparisons

Claude 4.1 Opus (Non-reasoning) vs Phi-3 Mini Instruct 3.8B

Anthropic vs Microsoft — side-by-side benchmark comparison

Claude 4.1 Opus (Non-reasoning)Phi-3 Mini Instruct 3.8B
Intelligence Index36.010.1
Coding Index3.0
Math Index0.3
Output speed (tok/s)44.70.0
Blended price ($/1M)$32.81$0.00
Time to first token (s)1.63s0.00s
aime4.0%
aime 250.3%
artificial analysis coding index3.00
artificial analysis intelligence index36.0010.10
artificial analysis math index30.0%
gpqa31.9%
hle4.4%
ifbench23.9%
lcr2.0%
livecodebench11.6%
math 50045.7%
mmlu pro43.5%
scicode9.0%
tau20.0%
terminalbench hard0.0%

Benchmark data from Artificial Analysis.