← All comparisons

Llama Nemotron Super 49B v1.5 (Reasoning) vs Qwen3.5 35B A3B (Non-reasoning)

NVIDIA vs Alibaba — side-by-side benchmark comparison

Llama Nemotron Super 49B v1.5 (Reasoning)Qwen3.5 35B A3B (Non-reasoning)
Intelligence Index18.730.7
Coding Index15.116.8
Math Index76.7
Output speed (tok/s)48.1147.9
Blended price ($/1M)$0.17$0.69
Time to first token (s)0.30s1.18s
aime86.0%
aime 2576.7%
artificial analysis coding index15.1016.80
artificial analysis intelligence index18.7030.70
artificial analysis math index76.70
gpqa74.8%81.9%
hle6.8%12.8%
ifbench37.0%44.5%
lcr34.0%55.3%
livecodebench73.7%
math 50098.3%
mmlu pro81.4%
scicode34.8%29.3%
tau228.1%86.3%
terminalbench hard5.3%10.6%

Benchmark data from Artificial Analysis.