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 |
| Benchmarks | ||
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. | 55% | 51.78% |
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. | 77.4% | 71.1% |
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. | 67.3% | 66.7% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 89.5% | 89.52% |
Gray Swan IPI · k = 1Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | 2.9% | — |
Gray Swan IPI · k = 10Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | 14.3% | — |
Gray Swan IPI · k = 15Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | 16.5% | — |
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. | — | 67.72% |
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | 10% | — |
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. | — | 88.22% |
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. | 82.2% | — |
JobBenchProfessional tool use — Tests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | 17% | — |
Toolathlon-VerifiedPersonal tool use — Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | 49.4% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 78% |
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. | 50.4% | — |
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. | 42.5% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 70.86% |
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. | 53.3% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 88.9% | — |
BabyVisionVisual reasoning — Tests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better. | 39.9% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 80.4% | — |
| Overview | ||
| Company | Meta | NVIDIA |
| Release date | Apr 8 2026 | Oct 15 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Muse SparkvsClaude Haiku 5.5Nemotron 3.5 Super VLvsClaude Haiku 5.5Muse SparkvsGPT-6.1 SolNemotron 3.5 Super VLvsGPT-6.1 SolMuse SparkvsGemini 4 ArgonNemotron 3.5 Super VLvsGemini 4 ArgonMuse SparkvsGrok 4.7Nemotron 3.5 Super VLvsGrok 4.7Muse SparkvsDeepSeek-V4.1-FlashNemotron 3.5 Super VLvsDeepSeek-V4.1-FlashMuse SparkvsMistral Large 4Nemotron 3.5 Super VLvsMistral Large 4Frequently asked questions
Muse Spark leads Nemotron 3.5 Super VL on 3 of the 4 benchmarks they both report (SWE-Bench Pro, SWE-Bench Verified, Terminal-Bench 2.1, GPQA Diamond). Muse Spark shipped 190 days before Nemotron 3.5 Super VL, so benchmark comparisons should account for the intervening progress.
Muse Spark is closed, while Nemotron 3.5 Super VL is open weight.
On SWE-Bench Pro, Muse Spark leads at 55% vs Nemotron 3.5 Super VL at 51.78%. On SWE-Bench Verified, Muse Spark leads at 77.4% vs Nemotron 3.5 Super VL at 71.1%. On Terminal-Bench 2.1, Muse Spark leads at 67.3% vs Nemotron 3.5 Super VL at 66.7%. On GPQA Diamond, Nemotron 3.5 Super VL leads at 89.52% vs Muse Spark at 89.5%.