Compare AI models
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | 120B | — |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 1M | — |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
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. | — | $2.50 |
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. | — | $0.20 |
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. | $0.08DekaLLM | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.40DeepInfra | — |
| $37.00DeepInfra · bf16 | $375SpaceXSI list price | |
| Benchmarks | ||
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. | 54% | 56% |
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. | 60.5% | 76.7% |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 53.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 79.2% | — |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | 36 | — |
| Overview | ||
| Company | NVIDIA | SpaceXSI |
| Release date | Mar 11 2026 | Feb 17 2026 |
| Access | Open Source | Closed |
| Model details | View model | View model |
Other comparisons
Nemotron 3 SupervsClaude Haiku 5.5Grok 4.20 BetavsClaude Haiku 5.5Nemotron 3 SupervsGPT-6.1 SolGrok 4.20 BetavsGPT-6.1 SolNemotron 3 SupervsGemini 4 ArgonGrok 4.20 BetavsGemini 4 ArgonNemotron 3 SupervsMuse WonderGrok 4.20 BetavsMuse WonderNemotron 3 SupervsDeepSeek-V4.1-FlashGrok 4.20 BetavsDeepSeek-V4.1-FlashNemotron 3 SupervsMistral Large 4Grok 4.20 BetavsMistral Large 4Frequently asked questions
Grok 4.20 Beta leads Nemotron 3 Super on 2 of the 2 benchmarks they both report (BullshitBench v2, SWE-Bench Verified). Only Grok 4.20 Beta has a verified first-party API price: $1.25 per million input tokens and $2.50 per million output tokens. No pay-as-you-go API rate is tracked for Nemotron 3 Super. Grok 4.20 Beta shipped 22 days before Nemotron 3 Super, so benchmark comparisons should account for the intervening progress.
Nemotron 3 Super is open source, while Grok 4.20 Beta is closed.
On BullshitBench v2, Grok 4.20 Beta leads at 56% vs Nemotron 3 Super at 54%. On SWE-Bench Verified, Grok 4.20 Beta leads at 76.7% vs Nemotron 3 Super at 60.5%.