← All comparisons

Claude 4.5 Haiku (Reasoning) vs Phi-3 Mini Instruct 3.8B

Anthropic vs Microsoft — side-by-side benchmark comparison

Claude 4.5 Haiku (Reasoning)Phi-3 Mini Instruct 3.8B
Intelligence Index37.110.1
Coding Index32.63.0
Math Index83.70.3
Output speed (tok/s)142.20.0
Blended price ($/1M)$2.19$0.00
Time to first token (s)10.48s0.00s
aime4.0%
aime 2583.7%0.3%
artificial analysis coding index32.603.00
artificial analysis intelligence index37.1010.10
artificial analysis math index83.7030.0%
gpqa67.2%31.9%
hle9.7%4.4%
ifbench54.3%23.9%
lcr70.3%2.0%
livecodebench61.5%11.6%
math 50045.7%
mmlu pro76.0%43.5%
scicode43.3%9.0%
tau254.7%0.0%
terminalbench hard27.3%0.0%

Benchmark data from Artificial Analysis.