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. | 30B | 550B |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.30DeepInfra | $0.50DeepInfra |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $1.10Phala | $2.20DeepInfra |
| 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. | 76% | 71.9% |
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. | 51.7% | 56.4% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 83.5% | 86.7% |
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. | 51.2% | — |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | 75.5% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 44.4% |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 22% | — |
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. | — | 26.7% |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 65.9% | — |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | — | 48 |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 953 | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 78.8% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 74% | — |
| Overview | ||
| Company | Meta | NVIDIA |
| Release date | Aug 10 2026 | Jun 4 2026 |
| Access | Open Weight | Open Source |
| Model details | View model | View model |
Other comparisons
Muse GlimmervsClaude Haiku 5.5Nemotron 3 UltravsClaude Haiku 5.5Muse GlimmervsGPT-6.1 SolNemotron 3 UltravsGPT-6.1 SolMuse GlimmervsGemini 4 ArgonNemotron 3 UltravsGemini 4 ArgonMuse GlimmervsGrok 4.7Nemotron 3 UltravsGrok 4.7Muse GlimmervsDeepSeek-V4.1-FlashNemotron 3 UltravsDeepSeek-V4.1-FlashMuse GlimmervsMistral Large 4Nemotron 3 UltravsMistral Large 4Frequently asked questions
Nemotron 3 Ultra leads Muse Glimmer on 2 of the 3 benchmarks they both report (SWE-Bench Verified, Terminal-Bench 2.1, GPQA Diamond). Nemotron 3 Ultra shipped 67 days before Muse Glimmer, so benchmark comparisons should account for the intervening progress.
Muse Glimmer has 30B parameters, while Nemotron 3 Ultra has 550B. Muse Glimmer is open weight, while Nemotron 3 Ultra is open source.
On SWE-Bench Verified, Muse Glimmer leads at 76% vs Nemotron 3 Ultra at 71.9%. On Terminal-Bench 2.1, Nemotron 3 Ultra leads at 56.4% vs Muse Glimmer at 51.7%. On GPQA Diamond, Nemotron 3 Ultra leads at 86.7% vs Muse Glimmer at 83.5%.