← All comparisons

Llama 4 Scout vs Claude 3.5 Sonnet (Oct '24)

Meta vs Anthropic — side-by-side benchmark comparison

Llama 4 ScoutClaude 3.5 Sonnet (Oct '24)
Intelligence Index13.515.9
Coding Index6.730.2
Math Index14.0
Output speed (tok/s)113.80.0
Blended price ($/1M)$0.29$6.56
Time to first token (s)0.56s0.00s
aime28.3%15.7%
aime 2514.0%
artificial analysis coding index6.7030.20
artificial analysis intelligence index13.5015.90
artificial analysis math index14.00
gpqa58.7%59.9%
hle4.3%3.9%
ifbench39.5%
lcr25.8%
livecodebench29.9%38.1%
math 50084.4%77.1%
mmlu pro75.2%77.2%
scicode17.0%36.6%
tau215.5%
terminalbench hard1.5%

Benchmark data from Artificial Analysis.