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. | — | 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. | 1M | 1M |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $1.50 | — |
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. | $7.50 | — |
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. | $0.075 | — |
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. | — | $1.25BaseTen |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $4.25BaseTen |
| $675Google list price | $463Modal | |
| These models have no shared benchmark scores. | ||
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% |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | — | 93% |
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% |
Terminal-Bench-Science 0.1Agentic scientific computing — The same command-line setup as Terminal-Bench, pointed at scientific work: the AI has to drive research tooling and computational workflows through to a result, rather than administer a machine. Version 0.1 is the first release of the task set, and scores run lower than on the general board. Higher is better. | 51.4% | — |
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% |
OSWorld 2.1 · offlineAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.1, in its offline setting. Scores are not comparable with version 2.0. Higher is better. | 77.6% | — |
AutomationBench (Artificial Analysis)Business workflows — The same business-workflow test, run by Artificial Analysis rather than by the lab, and graded strict pass@1: a workflow counts only if the whole of it is right on the first attempt. Read it as a separate board from the lab-run AutomationBench scores. Higher is better. | 76.1% | — |
Vending-Bench 2 (USD)Business simulation — ending bank balance in US dollars in Andon Labs’ vending-business simulation; higher is better | 14549 | — |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | — | 1401 |
Chartography · no toolsChart tasks — The same chart-centred test with no tools: the AI has to read each chart unaided. Scores run far lower than the with-tools version, so read the two as separate tests. Higher is better. | 66.6% | — |
ZeroBench (tools, pass@5)Visual reasoning — percentage of 100 visual problems solved at least once in five attempts with tools | — | 50% |
SimpleVQA (with tools)Visual reasoning — accuracy on 2,024 English and Chinese visual questions with tools | — | 73.6% |
BabyVision (with tools)Visual reasoning — mean accuracy on 388 visual reasoning questions with tools | — | 80.2% |
HLE-Diamond (no tools)Reasoning — accuracy on the 1,000-question HLE-Diamond reasoning and knowledge subset without tools | — | 26.1% |
| Overview | ||
| Company | Meta | |
| Release date | Nov 12 2026 | Oct 15 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 4 HydrogenvsClaude Fable 5.2Muse Spark OpenvsClaude Fable 5.2Gemini 4 HydrogenvsGPT-6.1 TerraMuse Spark OpenvsGPT-6.1 TerraGemini 4 HydrogenvsGrok 4.7Muse Spark OpenvsGrok 4.7Gemini 4 HydrogenvsDeepSeek-V4.1-Flash-1017Muse Spark OpenvsDeepSeek-V4.1-Flash-1017Gemini 4 HydrogenvsMistral Large 4Muse Spark OpenvsMistral Large 4Gemini 4 HydrogenvsKimi K3.1 ProMuse Spark OpenvsKimi K3.1 ProFrequently asked questions
Gemini 4 Hydrogen and Muse Spark Open don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Gemini 4 Hydrogen has a verified first-party price for an available API: $1.50 per million input tokens and $7.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for Muse Spark Open. Muse Spark Open shipped 28 days before Gemini 4 Hydrogen, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 4 Hydrogen) vs 1M (Muse Spark Open). Gemini 4 Hydrogen is closed, while Muse Spark Open is open weight.
Direct benchmark comparisons are unavailable — Gemini 4 Hydrogen and Muse Spark Open don't publish scores on any of the same benchmarks.