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. | 8B/70B/405B | 816B |
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. | 128k | 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. | $0.02DeepInfra | $1.25BaseTen |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.04DeepInfra | $4.25BaseTen |
| $6.00DeepInfra · fp8 | $463Modal | |
| These models have no shared benchmark scores. | ||
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. | 14% | — |
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% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | — | 1401 |
| Overview | ||
| Company | Meta | Meta |
| Release date | Jul 23 2024 | Oct 15 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
LLaMA 3.1vsClaude Haiku 5.5Muse Spark OpenvsClaude Haiku 5.5LLaMA 3.1vsGPT-6.1 SolMuse Spark OpenvsGPT-6.1 SolLLaMA 3.1vsGemini 4 ArgonMuse Spark OpenvsGemini 4 ArgonLLaMA 3.1vsGrok 4.7Muse Spark OpenvsGrok 4.7LLaMA 3.1vsDeepSeek-V4.1-Flash-1017Muse Spark OpenvsDeepSeek-V4.1-Flash-1017LLaMA 3.1vsMistral Large 4Muse Spark OpenvsMistral Large 4Frequently asked questions
LLaMA 3.1 and Muse Spark Open don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. LLaMA 3.1 shipped 814 days before Muse Spark Open, so benchmark comparisons should account for the intervening progress.
LLaMA 3.1 has 8B/70B/405B parameters, while Muse Spark Open has 816B. Context windows are 128k (LLaMA 3.1) vs 1M (Muse Spark Open).
Direct benchmark comparisons are unavailable — LLaMA 3.1 and Muse Spark Open don't publish scores on any of the same benchmarks.