← All comparisons

Llama 4 Maverick vs Claude 4.5 Haiku (Reasoning)

Meta vs Anthropic — side-by-side benchmark comparison

Llama 4 MaverickClaude 4.5 Haiku (Reasoning)
Intelligence Index18.437.1
Coding Index15.632.6
Math Index19.383.7
Output speed (tok/s)119.7142.2
Blended price ($/1M)$0.47$2.19
Time to first token (s)0.64s10.48s
aime39.0%
aime 2519.3%83.7%
artificial analysis coding index15.6032.60
artificial analysis intelligence index18.4037.10
artificial analysis math index19.3083.70
gpqa67.1%67.2%
hle4.8%9.7%
ifbench43.0%54.3%
lcr46.0%70.3%
livecodebench39.7%61.5%
math 50088.9%
mmlu pro80.9%76.0%
scicode33.1%43.3%
tau217.8%54.7%
terminalbench hard6.8%27.3%

Benchmark data from Artificial Analysis.