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. | 816B | 30B |
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 | 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. | — | $0.025Darkbloom |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.12Darkbloom |
| — | $11.00Darkbloom · int4 | |
| These models have no shared benchmark scores. | ||
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. | — | 51.6% |
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. | 60% | — |
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. | 76.4% | — |
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. | 89.2% | — |
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. | 61.8% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 75.4% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 1401 | — |
| Overview | ||
| Company | Meta | NVIDIA |
| Release date | Oct 15 2026 | Aug 11 2026 |
| Access | Open Weight | Open Source |
| Model details | View model | View model |
Other comparisons
Muse Spark OpenvsClaude Haiku 5.5Nemotron 3.5 LightningvsClaude Haiku 5.5Muse Spark OpenvsGPT-6.1 SolNemotron 3.5 LightningvsGPT-6.1 SolMuse Spark OpenvsGemini 4 ArgonNemotron 3.5 LightningvsGemini 4 ArgonMuse Spark OpenvsGrok 4.7Nemotron 3.5 LightningvsGrok 4.7Muse Spark OpenvsDeepSeek-V4.1-FlashNemotron 3.5 LightningvsDeepSeek-V4.1-FlashMuse Spark OpenvsMistral Large 4Nemotron 3.5 LightningvsMistral Large 4Frequently asked questions
Muse Spark Open and Nemotron 3.5 Lightning don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Nemotron 3.5 Lightning shipped 65 days before Muse Spark Open, so benchmark comparisons should account for the intervening progress.
Muse Spark Open has 816B parameters, while Nemotron 3.5 Lightning has 30B. Context windows are 1M (Muse Spark Open) vs 1M (Nemotron 3.5 Lightning). Muse Spark Open is open weight, while Nemotron 3.5 Lightning is open source.
Direct benchmark comparisons are unavailable — Muse Spark Open and Nemotron 3.5 Lightning don't publish scores on any of the same benchmarks.