← All comparisons

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) vs MiniMax M1 40k

NVIDIA vs MiniMax — side-by-side benchmark comparison

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)MiniMax M1 40k
Intelligence Index15.020.9
Coding Index13.114.1
Math Index63.713.7
Output speed (tok/s)52.30.0
Blended price ($/1M)$0.90$0.00
Time to first token (s)0.76s0.00s
aime74.7%81.3%
aime 2563.7%13.7%
artificial analysis coding index13.1014.10
artificial analysis intelligence index15.0020.90
artificial analysis math index63.7013.70
gpqa72.8%68.2%
hle8.1%7.5%
ifbench38.2%41.2%
lcr7.3%51.7%
livecodebench64.1%65.7%
math 50095.2%97.2%
mmlu pro82.5%80.8%
scicode34.7%37.8%
tau211.4%31.6%
terminalbench hard2.3%2.3%

Benchmark data from Artificial Analysis.