Nemotron Labs Dory 1.0 (4B) (Reasoning)

by NVIDIA

Nemotron Labs Dory 1.0 (4B) (Reasoning) is a reasoning model from NVIDIA, released on October 16, 2026. It ranks #135 of 247 models by Intelligence Score with a score of 21.8.

NVIDIA Nemotron Labs Dory 1.0 4B is an open-weight looped (latent-recurrent) normalized-GPT language model with interleaved sliding-window attention (SWA) and full-attention layers. A shared recurrent block can be applied multiple times at inference (recommended default: 2 loops) to trade compute for accuracy without swapping checkpoints. Text-in / text-out, English, up to 256K context (max_position_embeddings 262144). Reasoning model with tool calling. Pre-trained on 6T tokens (NVFP4 then BF16) plus 300B context-extension tokens; training data collected through December 2025. Released under OpenMDW License Agreement v1.1. Weights: BF16 (siblings MXFP8, NVFP4, GGUF).

Key specs

ProviderNVIDIA
Release date2026-10-16
Licenseopen weights
Intelligence Score21.8
Coding index4.5

Quick answers

Is Nemotron Labs Dory 1.0 (4B) (Reasoning) open source?

Yes. Nemotron Labs Dory 1.0 (4B) (Reasoning) is an open model released under the open weights license.

When was Nemotron Labs Dory 1.0 (4B) (Reasoning) released?

NVIDIA released Nemotron Labs Dory 1.0 (4B) (Reasoning) on October 16, 2026.

How does Nemotron Labs Dory 1.0 (4B) (Reasoning) compare to Claude Opus 5.5 (Reasoning)?

Nemotron Labs Dory 1.0 (4B) (Reasoning) scores 21.8 on the Intelligence Score versus 59.9 for Claude Opus 5.5 (Reasoning), the current #1.

Compare on the AI leaderboard · All AI models

More models from NVIDIA