← All comparisons

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) vs Qwen3.6 Max Preview

NVIDIA vs Alibaba — side-by-side benchmark comparison

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)Qwen3.6 Max Preview
Intelligence Index15.051.8
Coding Index13.144.9
Math Index63.7
Output speed (tok/s)52.338.7
Blended price ($/1M)$0.90$2.92
Time to first token (s)0.76s1.96s
aime74.7%
aime 2563.7%
artificial analysis coding index13.1044.90
artificial analysis intelligence index15.0051.80
artificial analysis math index63.70
gpqa72.8%88.8%
hle8.1%28.9%
ifbench38.2%76.6%
lcr7.3%69.7%
livecodebench64.1%
math 50095.2%
mmlu pro82.5%
scicode34.7%46.9%
tau211.4%95.9%
terminalbench hard2.3%43.9%

Benchmark data from Artificial Analysis.