Compare AI models

Specifications
Parameters
120B7B/14B
Context window
1M1M
API pricing
Cheapest input
$0.06DeepInfra—
Cheapest output
$0.32DeepInfra—
$35.00DeepInfra · bf16—
Benchmarks
LiveCodeBench
81.19%38.6%
MMLU-Pro
83.73%63.3%
Overview
CompanyNVIDIAQwen
Release dateMar 11 2026Jan 27 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Nemotron 3 Super leads Qwen2.5-1M on 2 of the 2 benchmarks they both report (LiveCodeBench, MMLU-Pro). Qwen2.5-1M shipped 408 days before Nemotron 3 Super, so benchmark comparisons should account for the intervening progress.

Nemotron 3 Super has 120B parameters, while Qwen2.5-1M has 7B/14B. Context windows are 1M (Nemotron 3 Super) vs 1M (Qwen2.5-1M).

On LiveCodeBench, Nemotron 3 Super leads at 81.19% vs Qwen2.5-1M at 38.6%. On MMLU-Pro, Nemotron 3 Super leads at 83.73% vs Qwen2.5-1M at 63.3%.