← All comparisons

Llama Nemotron Super 49B v1.5 (Non-reasoning) vs Qwen3.5 27B (Reasoning)

NVIDIA vs Alibaba — side-by-side benchmark comparison

Llama Nemotron Super 49B v1.5 (Non-reasoning)Qwen3.5 27B (Reasoning)
Intelligence Index14.642.1
Coding Index10.534.9
Math Index8.0
Output speed (tok/s)48.984.3
Blended price ($/1M)$0.17$0.82
Time to first token (s)0.28s1.37s
aime13.7%
aime 258.0%
artificial analysis coding index10.5034.90
artificial analysis intelligence index14.6042.10
artificial analysis math index8.00
gpqa48.1%85.8%
hle4.3%22.2%
ifbench32.9%75.6%
lcr22.0%67.3%
livecodebench29.0%
math 50077.0%
mmlu pro69.2%
scicode23.8%39.5%
tau225.1%93.9%
terminalbench hard3.8%32.6%

Benchmark data from Artificial Analysis.