← All comparisons

Claude 4.5 Haiku (Reasoning) vs Claude 4 Opus (Reasoning)

Anthropic vs Anthropic — side-by-side benchmark comparison

Claude 4.5 Haiku (Reasoning)Claude 4 Opus (Reasoning)
Intelligence Index37.139.0
Coding Index32.634.0
Math Index83.773.3
Output speed (tok/s)142.242.1
Blended price ($/1M)$2.19$32.81
Time to first token (s)10.48s6.80s
aime75.7%
aime 2583.7%73.3%
artificial analysis coding index32.6034.00
artificial analysis intelligence index37.1039.00
artificial analysis math index83.7073.30
gpqa67.2%79.6%
hle9.7%11.7%
ifbench54.3%53.7%
lcr70.3%33.7%
livecodebench61.5%63.6%
math 50098.2%
mmlu pro76.0%87.3%
scicode43.3%39.8%
tau254.7%73.4%
terminalbench hard27.3%31.1%

Benchmark data from Artificial Analysis.