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. | 70B | 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. | $0.10DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.32DeepInfra | — |
| $36.00DeepInfra · turbo · fp8 | — | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 50.5% | 72.41% |
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% |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 88.4% | — |
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% |
MATHReasoning — accuracy on the original competition mathematics test set | 77% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 77.94% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 68.9% | — |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 86% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 91.1% | — |
| Overview | ||
| Company | Meta | NVIDIA |
| Release date | Dec 6 2024 | Oct 16 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
LLaMA 3.3vsClaude Fable 5.2Nemotron Labs Dory 1.0 4BvsClaude Fable 5.2LLaMA 3.3vsGPT-6.1 TerraNemotron Labs Dory 1.0 4BvsGPT-6.1 TerraLLaMA 3.3vsGemini 4 CarbonNemotron Labs Dory 1.0 4BvsGemini 4 CarbonLLaMA 3.3vsGrok 4.7Nemotron Labs Dory 1.0 4BvsGrok 4.7LLaMA 3.3vsDeepSeek-V4.1-Flash-1017Nemotron Labs Dory 1.0 4BvsDeepSeek-V4.1-Flash-1017LLaMA 3.3vsMistral Large 4Nemotron Labs Dory 1.0 4BvsMistral Large 4Frequently asked questions
Nemotron Labs Dory 1.0 4B leads LLaMA 3.3 on 1 of the 1 benchmark they both report (GPQA Diamond). LLaMA 3.3 shipped 679 days before Nemotron Labs Dory 1.0 4B, so benchmark comparisons should account for the intervening progress.
LLaMA 3.3 has 70B parameters, while Nemotron Labs Dory 1.0 4B has 4B. Context windows are 128k (LLaMA 3.3) vs 256k (Nemotron Labs Dory 1.0 4B).
On GPQA Diamond, Nemotron Labs Dory 1.0 4B leads at 72.41% vs LLaMA 3.3 at 50.5%.