Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 4B | 0.8B/2B/4B/9B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 256k | 256k |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 72.41% | 81.7% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 77.94% | 64.5% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 59.5% | — |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 65.6% |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 18.1% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 91.5% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 10.89% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 82.5% |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 41.8% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 73% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 70.1% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 78.4% |
| Overview | ||
| Company | NVIDIA | Qwen |
| Release date | Oct 16 2026 | Mar 2 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Nemotron Labs Dory 1.0 4BvsClaude Fable 5.2Qwen3.5 SmallvsClaude Fable 5.2Nemotron Labs Dory 1.0 4BvsGPT-6.2 AstraQwen3.5 SmallvsGPT-6.2 AstraNemotron Labs Dory 1.0 4BvsGemini 4 NeonQwen3.5 SmallvsGemini 4 NeonNemotron Labs Dory 1.0 4BvsMuse EmberQwen3.5 SmallvsMuse EmberNemotron Labs Dory 1.0 4BvsGrok 4.7Qwen3.5 SmallvsGrok 4.7Nemotron Labs Dory 1.0 4BvsDeepSeek-V4.1-Flash-1017Qwen3.5 SmallvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Nemotron Labs Dory 1.0 4B and Qwen3.5 Small are evenly matched across the 2 benchmarks they both report (GPQA Diamond, IFBench). Qwen3.5 Small shipped 228 days before Nemotron Labs Dory 1.0 4B, so benchmark comparisons should account for the intervening progress.
Nemotron Labs Dory 1.0 4B has 4B parameters, while Qwen3.5 Small has 0.8B/2B/4B/9B. Context windows are 256k (Nemotron Labs Dory 1.0 4B) vs 256k (Qwen3.5 Small).
On GPQA Diamond, Qwen3.5 Small leads at 81.7% vs Nemotron Labs Dory 1.0 4B at 72.41%. On IFBench, Nemotron Labs Dory 1.0 4B leads at 77.94% vs Qwen3.5 Small at 64.5%.