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. | — | 2.8T |
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 · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $0.10 | $2.00 |
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. | $0.50 | $10.00 |
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. | $0.004 | $0.20 |
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. | — | $0.2869Relace |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $8.2509Relace |
| $45.00Meta list price | $470Relace · fp4 | |
| Benchmarks | ||
Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. | 40.9% | 65.7% |
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. | — | 75.5% |
SWE-Marathon v1.1Multi-hour coding — Twenty multi-hour programming jobs — rebuilding a library, cloning a product, training a model, making something faster. A run counts only when every check passes, hidden tests and interface review included. Higher is better. | — | 51.7% |
AA Coding Agent IndexAgentic coding — Artificial Analysis' overall score for coding agents, combining three coding benchmarks with what each run costs and how many tokens it burns. It rates a model paired with a particular agent harness rather than the model alone, so the same model scores differently in different tools. Higher is better. | 46 | — |
BenchCADCAD programming — Can the AI do mechanical design as code? Given a drawing or a description of an industrial part — a gear, a spring, a drill bit — it has to write or edit the parametric CAD program that builds it, and the program is run to check the shape really comes out right. Higher is better. | — | 92.7% |
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. | — | 38.1% |
APEX-AgentsExpert agentic work — expert-level agentic work tasks (AI Productivity Index) | — | 67.2% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 92.1% |
ExploitBenchCybersecurity — A 'capability ladder' for security research, built by CMU researchers: the AI is given known bugs in Chrome's V8 engine and scored on how far it gets toward a working exploit inside a research sandbox — from understanding the patch to triggering a crash. Higher is better. | — | 74.7% |
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. | — | 51.1% |
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. | — | 70% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 94.2% |
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. | 37.8% | — |
AA Intelligence Index v5.0Overall intelligence — Artificial Analysis composite intelligence index, version 5.0 with tools; separate from earlier index editions | 36 | — |
GDPval-AA v2.1Knowledge work — economically valuable knowledge work (v2.1, Crowd-BT Elo fit) | — | 1846 |
AA-Briefcase v1.1Knowledge work — Artificial Analysis agentic office-work eval (Elo, v1.1 rating fit) | — | 1678 |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 89% |
CharXiv Reasoning · with toolsChart reasoning — The same chart-and-figure reasoning test, run with the AI allowed to use tools — writing code to inspect the image, for instance — rather than reading the chart unaided. Scores run higher than the unaided version, so read the two as separate tests. Higher is better. | — | 93.4% |
Chartography · with toolsChart tasks — A chart-centred test run with tools available to the AI, reported separately from the chart-reading benchmarks above it. Higher is better. | — | 90.2% |
OfficeQA ProDocument Q&A — Questions about office documents, where answering depends on reading the page as a document — layout, tables and figures included — rather than as loose text. Higher is better. | — | 67.4% |
GDP.PDFDocument comprehension — Real professional PDFs — filings, reports, technical documents — with questions an expert in that field would ask. Tests whether the AI reads the page as a document, layout and figures included, rather than as loose text. Higher is better. | — | 34.6% |
GDP.PDF (Artificial Analysis)Document comprehension — The same professional-PDF test, run by Artificial Analysis rather than by the lab. Read it as a separate board from the lab-run GDP.PDF scores. Higher is better. | 22.8% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 84.1% |
| Overview | ||
| Company | Meta | Moonshot AI |
| Release date | Nov 9 2026 | Oct 23 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Muse EmbervsClaude Fable 5.2Kimi K3.1 ProvsClaude Fable 5.2Muse EmbervsGPT-6.1 TerraKimi K3.1 ProvsGPT-6.1 TerraMuse EmbervsGemini 4 CarbonKimi K3.1 ProvsGemini 4 CarbonMuse EmbervsGrok 4.7Kimi K3.1 ProvsGrok 4.7Muse EmbervsDeepSeek-V4.1-Flash-1017Kimi K3.1 ProvsDeepSeek-V4.1-Flash-1017Muse EmbervsMistral Large 4Kimi K3.1 ProvsMistral Large 4Frequently asked questions
Kimi K3.1 Pro leads Muse Ember on 1 of the 1 benchmark they both report (Terminal-Bench 4.0). Muse Ember is cheaper on both input and output: $0.10 vs $2.00 per million input tokens, and $0.50 vs $10.00 per million output tokens. Figures are base-tier rates. Kimi K3.1 Pro shipped 17 days before Muse Ember, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Muse Ember) vs 1M (Kimi K3.1 Pro). Muse Ember is closed, while Kimi K3.1 Pro is open weight.
On Terminal-Bench 4.0, Kimi K3.1 Pro leads at 65.7% vs Muse Ember at 40.9%.