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
Text 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: NVIDIA: Nemotron 3 Ultra T
Reasoning Tools Open weights 67.7

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

nvidia/nemotron-3-ultra-550b-a55b 2026-06-04 256K context $0.625/M input $3.125/M output
15 providers
Poolside: Poolside: Laguna XS 2.1 T
Reasoning Tools Open weights 63.1

Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...

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