← All comparisons

Llama 3.3 Instruct 70B vs Claude 4.1 Opus (Reasoning)

Meta vs Anthropic — side-by-side benchmark comparison

Llama 3.3 Instruct 70BClaude 4.1 Opus (Reasoning)
Intelligence Index14.542.0
Coding Index10.736.5
Math Index7.780.3
Output speed (tok/s)88.144.5
Blended price ($/1M)$0.62$32.81
Time to first token (s)0.59s8.55s
aime30.0%
aime 257.7%80.3%
artificial analysis coding index10.7036.50
artificial analysis intelligence index14.5042.00
artificial analysis math index7.7080.30
gpqa49.8%80.9%
hle4.0%11.9%
ifbench47.1%55.4%
lcr15.0%66.3%
livecodebench28.8%65.4%
math 50077.3%
mmlu pro71.3%88.0%
scicode26.0%40.9%
tau226.6%71.4%
terminalbench hard3.0%34.3%

Benchmark data from Artificial Analysis.