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 | >1T |
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 | ||
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% | 75.3% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 10.89% | 30.2% |
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% | 87.4% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 77.94% | 70.9% |
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. | — | 85.9% |
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% | — |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 49.8% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 85.7% |
| Overview | ||
| Company | NVIDIA | Qwen |
| Release date | Oct 16 2026 | Jan 26 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Nemotron Labs Dory 1.0 4BvsClaude Fable 5.2Qwen3-Max-ThinkingvsClaude Fable 5.2Nemotron Labs Dory 1.0 4BvsGPT-6.2 AstraQwen3-Max-ThinkingvsGPT-6.2 AstraNemotron Labs Dory 1.0 4BvsGemini 4 NeonQwen3-Max-ThinkingvsGemini 4 NeonNemotron Labs Dory 1.0 4BvsMuse EmberQwen3-Max-ThinkingvsMuse EmberNemotron Labs Dory 1.0 4BvsGrok 4.7Qwen3-Max-ThinkingvsGrok 4.7Nemotron Labs Dory 1.0 4BvsDeepSeek-V4.1-Flash-1017Qwen3-Max-ThinkingvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3-Max-Thinking leads Nemotron Labs Dory 1.0 4B on 3 of the 4 benchmarks they both report (SWE-Bench Verified, Humanity's Last Exam, GPQA Diamond, IFBench). Qwen3-Max-Thinking shipped 263 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-Max-Thinking has >1T. Context windows are 256k (Nemotron Labs Dory 1.0 4B) vs 256k (Qwen3-Max-Thinking). Nemotron Labs Dory 1.0 4B is open weight, while Qwen3-Max-Thinking is closed.
On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs Nemotron Labs Dory 1.0 4B at 59.5%. On Humanity's Last Exam · text only, no tools, Qwen3-Max-Thinking leads at 30.2% vs Nemotron Labs Dory 1.0 4B at 10.89%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs Nemotron Labs Dory 1.0 4B at 72.41%. On IFBench, Nemotron Labs Dory 1.0 4B leads at 77.94% vs Qwen3-Max-Thinking at 70.9%.