ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
2 models
NVIDIA perplexity-agent 200K+
NVIDIA: Nemotron 3.5 Super 120B A12B T
Reasoning Tools JSON Open weights

NVIDIA Nemotron 3.5 Super reasoning model (120B total, 12B active) served with text-only input

nvidia/nemotron-3.5-super-120b-a12b 2026-10-15 1.04858M context $0.2/M input $0.5/M output
1 provider
NVIDIA: Nemotron 3 Super 120B A12B T
Reasoning Tools JSON Open weights

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

nvidia/nemotron-3-super-120b-a12b 2026-03-11 262.144K context $0.05/M input $0.25/M output
17 providers