← All comparisons

Llama 3.1 Instruct 70B vs Claude 4.1 Opus (Non-reasoning)

Meta vs Anthropic — side-by-side benchmark comparison

Llama 3.1 Instruct 70BClaude 4.1 Opus (Non-reasoning)
Intelligence Index12.536.0
Coding Index10.9
Math Index4.0
Output speed (tok/s)35.344.7
Blended price ($/1M)$0.56$32.81
Time to first token (s)0.54s1.63s
aime17.3%
aime 254.0%
artificial analysis coding index10.90
artificial analysis intelligence index12.5036.00
artificial analysis math index4.00
gpqa40.9%
hle4.6%
ifbench34.4%
lcr6.3%
livecodebench23.2%
math 50064.9%
mmlu pro67.6%
scicode26.7%
tau215.2%
terminalbench hard3.0%

Benchmark data from Artificial Analysis.