NVIDIA model product
0 is a 4B open-weight English language model with looped latent-recurrent inference, interleaved sliding-window and full-attention layers, a 256K context window, reasoning, and tool calling.
Updated Oct 23, 2026. Default version: Nemotron Labs Dory 1.0 (4B)
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Nemotron Labs Dory 1.0 (4B).
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkOmniScience | Score10.08% | Rank07 | Participants7 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAA-LCR | Score71.00% | Rank08 | Participants27 | Percentile73.08% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score77.94% | Rank14 | Participants46 | Percentile71.11% | EvidenceC | Evaluated |
| BenchmarkTau3 Banking | Score12.89% | Rank14 | Participants16 | Percentile13.33% | EvidenceC | Evaluated |
| BenchmarkGDPval-AA | Score946.00 points | Rank17 | Participants17 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score34.94% | Rank28 | Participants31 | Percentile10.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score18.10% | Rank48 | Participants48 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score59.50% | Rank91 | Participants120 | Percentile24.37% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score10.89% | Rank97 | Participants109 | Percentile11.11% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score72.41% | Rank140 | Participants256 | Percentile45.49% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for Nemotron Labs Dory 1.0 (4B). Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionNemotron Labs Dory 1.0 (4B) | Released | LLMBoard37.05 | Parameters4B | ContextN/A | Max outputN/A | Open weightsYes | LicenseOpenMDW License v1.1 |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Nemotron Labs Dory 1.0 and its available data.
0 is an open-weight looped (latent-recurrent) normalized-GPT language model from NVIDIA that uses interleaved sliding-window attention (SWA) and full-attention layers. It supports text input and output in English, with a maximum context of 256K tokens and inference configured for multiple recurrent loops.
Data as of 2026-10-22.
Common questions about Nemotron Labs Dory 1.0.
Nemotron Labs Dory 1.0's default version was released on Oct 16, 2026.
No official standard PAYG price is currently available for Nemotron Labs Dory 1.0.
Nemotron Labs Dory 1.0 was created by NVIDIA.
A context window is not available for the default version.
Yes. The default version is marked as open weight under OpenMDW License v1.1.
No provider offering is currently linked to the default version.