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. | 671B | 4B |
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. | 128k | 256k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.50DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.15DeepInfra | — |
| $208DeepInfra · fp4 | — | |
| 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. | 57.6% | 59.5% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 81% | 72.41% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 8% | — |
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. | 73.3% | — |
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. | 17.7% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 77.94% |
| Overview | ||
| Company | DeepSeek | NVIDIA |
| Release date | May 28 2025 | Oct 16 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1-0528vsClaude Fable 5.2Nemotron Labs Dory 1.0 4BvsClaude Fable 5.2DeepSeek R1-0528vsGPT-6.1 TerraNemotron Labs Dory 1.0 4BvsGPT-6.1 TerraDeepSeek R1-0528vsGemini 4 CarbonNemotron Labs Dory 1.0 4BvsGemini 4 CarbonDeepSeek R1-0528vsMuse EmberNemotron Labs Dory 1.0 4BvsMuse EmberDeepSeek R1-0528vsGrok 4.7Nemotron Labs Dory 1.0 4BvsGrok 4.7DeepSeek R1-0528vsMistral Large 4Nemotron Labs Dory 1.0 4BvsMistral Large 4Frequently asked questions
DeepSeek R1-0528 and Nemotron Labs Dory 1.0 4B are evenly matched across the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). DeepSeek R1-0528 shipped 506 days before Nemotron Labs Dory 1.0 4B, so benchmark comparisons should account for the intervening progress.
DeepSeek R1-0528 has 671B parameters, while Nemotron Labs Dory 1.0 4B has 4B. Context windows are 128k (DeepSeek R1-0528) vs 256k (Nemotron Labs Dory 1.0 4B).
On SWE-Bench Verified, Nemotron Labs Dory 1.0 4B leads at 59.5% vs DeepSeek R1-0528 at 57.6%. On GPQA Diamond, DeepSeek R1-0528 leads at 81% vs Nemotron Labs Dory 1.0 4B at 72.41%.