← All comparisons

Llama 3.2 Instruct 90B (Vision) vs Claude 4.5 Haiku (Non-reasoning)

Meta vs Anthropic — side-by-side benchmark comparison

Llama 3.2 Instruct 90B (Vision)Claude 4.5 Haiku (Non-reasoning)
Intelligence Index11.931.0
Coding Index29.6
Math Index39.0
Output speed (tok/s)47.1105.8
Blended price ($/1M)$1.38$2.19
Time to first token (s)0.48s0.65s
aime5.0%
aime 2539.0%
artificial analysis coding index29.60
artificial analysis intelligence index11.9031.00
artificial analysis math index39.00
gpqa43.2%64.6%
hle4.9%4.3%
ifbench42.0%
lcr43.7%
livecodebench21.4%51.1%
math 50062.9%
mmlu pro67.1%80.0%
scicode24.0%34.4%
tau232.5%
terminalbench hard27.3%

Benchmark data from Artificial Analysis.