← All comparisons

Claude 4.1 Opus (Non-reasoning) vs Llama 3.1 Tulu3 405B

Anthropic vs Allen Institute for AI — side-by-side benchmark comparison

Claude 4.1 Opus (Non-reasoning)Llama 3.1 Tulu3 405B
Intelligence Index36.014.1
Coding Index——
Math Index——
Output speed (tok/s)44.70.0
Blended price ($/1M)$32.81$0.00
Time to first token (s)1.63s0.00s
aime—13.3%
aime 25——
artificial analysis coding index——
artificial analysis intelligence index36.0014.10
artificial analysis math index——
gpqa—51.6%
hle—3.5%
ifbench——
lcr——
livecodebench—29.1%
math 500—77.8%
mmlu pro—71.6%
scicode—30.2%
tau2——
terminalbench hard——

Benchmark data from Artificial Analysis.