← All comparisons

Llama Nemotron Super 49B v1.5 (Non-reasoning) vs Qwen2.5 Turbo

NVIDIA vs Alibaba — side-by-side benchmark comparison

Llama Nemotron Super 49B v1.5 (Non-reasoning)Qwen2.5 Turbo
Intelligence Index14.612.0
Coding Index10.5
Math Index8.0
Output speed (tok/s)48.966.5
Blended price ($/1M)$0.17$0.09
Time to first token (s)0.28s1.16s
aime13.7%12.0%
aime 258.0%
artificial analysis coding index10.50
artificial analysis intelligence index14.6012.00
artificial analysis math index8.00
gpqa48.1%41.0%
hle4.3%4.2%
ifbench32.9%
lcr22.0%
livecodebench29.0%16.3%
math 50077.0%80.5%
mmlu pro69.2%63.3%
scicode23.8%15.3%
tau225.1%
terminalbench hard3.8%

Benchmark data from Artificial Analysis.