← All comparisons

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) vs Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)

NVIDIA vs NVIDIA — side-by-side benchmark comparison

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)
Intelligence Index15.014.3
Coding Index13.17.6
Math Index63.77.7
Output speed (tok/s)52.30.0
Blended price ($/1M)$0.90$0.00
Time to first token (s)0.76s0.00s
aime74.7%19.3%
aime 2563.7%7.7%
artificial analysis coding index13.107.60
artificial analysis intelligence index15.0014.30
artificial analysis math index63.707.70
gpqa72.8%51.7%
hle8.1%3.5%
ifbench38.2%39.5%
lcr7.3%11.3%
livecodebench64.1%28.0%
math 50095.2%77.5%
mmlu pro82.5%69.8%
scicode34.7%22.9%
tau211.4%
terminalbench hard2.3%0.0%

Benchmark data from Artificial Analysis.