← All comparisons

Llama Nemotron Super 49B v1.5 (Reasoning) vs Jamba 1.6 Mini

NVIDIA vs AI21 Labs — side-by-side benchmark comparison

Llama Nemotron Super 49B v1.5 (Reasoning)Jamba 1.6 Mini
Intelligence Index18.77.9
Coding Index15.1
Math Index76.7
Output speed (tok/s)48.1188.1
Blended price ($/1M)$0.17$0.25
Time to first token (s)0.30s0.75s
aime86.0%3.3%
aime 2576.7%
artificial analysis coding index15.10
artificial analysis intelligence index18.707.90
artificial analysis math index76.70
gpqa74.8%30.0%
hle6.8%4.6%
ifbench37.0%
lcr34.0%
livecodebench73.7%7.1%
math 50098.3%25.7%
mmlu pro81.4%36.7%
scicode34.8%10.1%
tau228.1%
terminalbench hard5.3%

Benchmark data from Artificial Analysis.