← All comparisons

Claude 4.5 Haiku (Reasoning) vs Claude 4.1 Opus (Reasoning)

Anthropic vs Anthropic — side-by-side benchmark comparison

Claude 4.5 Haiku (Reasoning)Claude 4.1 Opus (Reasoning)
Intelligence Index37.142.0
Coding Index32.636.5
Math Index83.780.3
Output speed (tok/s)142.244.5
Blended price ($/1M)$2.19$32.81
Time to first token (s)10.48s8.55s
aime
aime 2583.7%80.3%
artificial analysis coding index32.6036.50
artificial analysis intelligence index37.1042.00
artificial analysis math index83.7080.30
gpqa67.2%80.9%
hle9.7%11.9%
ifbench54.3%55.4%
lcr70.3%66.3%
livecodebench61.5%65.4%
math 500
mmlu pro76.0%88.0%
scicode43.3%40.9%
tau254.7%71.4%
terminalbench hard27.3%34.3%

Benchmark data from Artificial Analysis.