ModelBench
Model catalog

Models

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

Compare Export CSV
5 models
128K+ Open weights
Ranked by SWE-Bench Multilingual
Deepreinforce: Ornith 1.0 397B T
Open weights 78.9

Large coding-reasoning model for agentic software tasks and RL search

deepreinforce/ornith-1.0-397b 2026-06-25 262.144K context Input not listed Output not listed
Deepreinforce: Ornith 1.0 35B T
Open weights 69.3

Large coding-reasoning model for agentic software tasks and RL search

deepreinforce/ornith-1.0-35b 2026-06-25 262.144K context Input not listed Output not listed
NVIDIA: Nemotron 3 Ultra 550B A55B T
Reasoning Tools Open weights 67.7

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

nvidia/nemotron-3-ultra-550b-a55b 2026-06-04 1M context $0.5/M input $2.5/M output
15 providers
Poolside: Laguna XS 2.1 T
Reasoning Tools Open weights 63.1

Agentic coding model from Poolside in the XS size class for local deployment

poolside/laguna-xs-2.1 2026-07-02 262.144K context $0.06/M input $0.12/M output
6 providers
Deepreinforce: Ornith 1.0 9B T
Open weights 52.0

Open coding-reasoning model for repository tasks and self-improving agents

deepreinforce/ornith-1.0-9b 2026-06-25 262.144K context Input not listed Output not listed