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 | — |
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 | 400k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $1.25 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $10.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.125 |
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. | — | $0.625OpenAI |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $5.00OpenAI |
| — | $750OpenAI list price | |
| Benchmarks | ||
τ²-bench · retailAgentic tasks — task success in the retail domain of the second-generation customer-service evaluation | 39.8% | 77.9% |
τ²-bench · airlineAgentic tasks — task success in the airline domain of the second-generation customer-service evaluation | 33.3% | 67% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 78.5% | 94% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 53.2% | 88.1% |
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. | — | 25% |
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. | — | 76.3% |
τ²-bench · telecomAgentic tasks — task success in the telecom domain of the second-generation customer-service evaluation | 33% | — |
τ²-bench · telecom, adjusted promptAgentic tasks — telecom task success with an extra general instruction in the system prompt | — | 95.6% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 95.4% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 85.4% |
| Overview | ||
| Company | NVIDIA | OpenAI |
| Release date | Mar 16 2026 | Nov 12 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Nemotron 3 Nano 4BvsClaude Fable 5.2GPT-5.1vsClaude Fable 5.2Nemotron 3 Nano 4BvsGemini 4 NeonGPT-5.1vsGemini 4 NeonNemotron 3 Nano 4BvsMuse EmberGPT-5.1vsMuse EmberNemotron 3 Nano 4BvsGrok 4.7GPT-5.1vsGrok 4.7Nemotron 3 Nano 4BvsDeepSeek-V4.1-Flash-1017GPT-5.1vsDeepSeek-V4.1-Flash-1017Nemotron 3 Nano 4BvsMistral Large 4GPT-5.1vsMistral Large 4Frequently asked questions
GPT-5.1 leads Nemotron 3 Nano 4B on 4 of the 4 benchmarks they both report (τ²-bench, AIME 2025, GPQA Diamond). Only GPT-5.1 has a verified first-party price for an available API: $1.25 per million input tokens and $10.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Nemotron 3 Nano 4B. GPT-5.1 shipped 124 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Nemotron 3 Nano 4B) vs 400k (GPT-5.1). Nemotron 3 Nano 4B is open weight, while GPT-5.1 is closed.
On τ²-bench · retail, GPT-5.1 leads at 77.9% vs Nemotron 3 Nano 4B at 39.8%. On τ²-bench · airline, GPT-5.1 leads at 67% vs Nemotron 3 Nano 4B at 33.3%. On AIME 2025, GPT-5.1 leads at 94% vs Nemotron 3 Nano 4B at 78.5%. On GPQA Diamond, GPT-5.1 leads at 88.1% vs Nemotron 3 Nano 4B at 53.2%.