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. | 550B | — |
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. | 1M | — |
| 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. | $0.40DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.76DeepInfra | — |
| $210KT | — | |
| Benchmarks | ||
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 86.8% | 72% |
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. | 49% | — |
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 49.66% | — |
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. | 71.9% | — |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 67.7% | — |
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. | 89% | — |
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. | — | 85.7% |
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. | 56.4% | — |
τ²-bench · retailAgentic tasks — task success in the retail domain of the second-generation customer-service evaluation | 73.68% | — |
τ²-bench · airlineAgentic tasks — task success in the airline domain of the second-generation customer-service evaluation | 79.75% | — |
τ²-bench · telecomAgentic tasks — task success in the telecom domain of the second-generation customer-service evaluation | 83% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 44.4% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 29.24% | — |
Humanity's Last Exam · text only, with toolsMultidisciplinary reasoning — The text-only questions from Humanity's Last Exam, answered with access to tools such as search or code execution. The score is the percentage answered correctly. | 37.4% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 73% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 87% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 82.94% | — |
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. | — | 86.2% |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | 48 | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | — | 68.1% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 63.2% |
| Overview | ||
| Company | NVIDIA | SpaceXSI |
| Release date | Jun 4 2026 | Aug 13 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Nemotron 3 UltravsClaude Fable 5.2Grok‑2 minivsClaude Fable 5.2Nemotron 3 UltravsGPT-6.2 AstraGrok‑2 minivsGPT-6.2 AstraNemotron 3 UltravsGemini 4 NeonGrok‑2 minivsGemini 4 NeonNemotron 3 UltravsMuse EmberGrok‑2 minivsMuse EmberNemotron 3 UltravsDeepSeek-V4.1-Flash-1017Grok‑2 minivsDeepSeek-V4.1-Flash-1017Nemotron 3 UltravsMistral Large 4Grok‑2 minivsMistral Large 4Frequently asked questions
Nemotron 3 Ultra leads Grok‑2 mini on 1 of the 1 benchmark they both report (MMLU-Pro). Grok‑2 mini shipped 660 days before Nemotron 3 Ultra, so benchmark comparisons should account for the intervening progress.
Nemotron 3 Ultra is open weight, while Grok‑2 mini is closed.
On MMLU-Pro, Nemotron 3 Ultra leads at 86.8% vs Grok‑2 mini at 72%.