Compare AI models
| Specifications | ||
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 | 400k |
| 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. | $1.25 | $0.25 |
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. | $4.25 | $2.00 |
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. | — | $0.025 |
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. | $1.25Meta | $0.125OpenAI |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $4.25Meta | $1.00OpenAI |
| $463Meta list price | $150OpenAI list price | |
| Benchmarks | ||
ProgramBenchProgram reconstruction — The AI receives a working program and its documentation, then builds a replacement from scratch without the original source code, internet access or decompilation. The score is the percentage of 200 programs that pass every behavioral test. We record each model's best published mini-SWE-agent result, including higher reasoning efforts where available. Partial test-pass rates and almost-solved programs do not count toward this score. Equal scores share a rank here; the official board also uses partial progress to break ties. Higher is better. | 0% | 0% |
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. | 88.4% | 75.5% |
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. | 61.5% | — |
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. | — | 71% |
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. | 53.3% | — |
Aider Polyglot (diff)Coding — editing code in six languages using the diff edit format | — | 71.6% |
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. | 80% | — |
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. | 88.1% | — |
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. | 54.7% | — |
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. | 75.6% | — |
τ²-bench · retailAgentic tasks — task success in the retail domain of the second-generation customer-service evaluation | — | 78.3% |
τ²-bench · airlineAgentic tasks — task success in the airline domain of the second-generation customer-service evaluation | — | 60% |
τ²-bench · telecomAgentic tasks — task success in the telecom domain of the second-generation customer-service evaluation | — | 74.1% |
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. | — | 16.7% |
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. | 62.1% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 91.1% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 82.3% |
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. | 80.8% | — |
Finance Agent v2Agentic financial analysis — Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 57.2% | — |
Harvey's Legal Agent BenchmarkAgentic legal work — Harvey's test of whether an AI agent can complete real legal work — drafting and reviewing documents, working with spreadsheets and presentations, and navigating files the way a lawyer's assistant would. Higher is better. | 20% | — |
TaxEval v2Tax questions — A set of real tax questions created by Vals AI — can the AI give accurate answers about tax rules and filings? Higher is better. | 79.72% | — |
HealthBench · hardHealthcare — physician rubric score on the hard subset of the original HealthBench evaluation | — | 40.3% |
MedScribeMedical admin work — Can the AI support doctors with their administrative work, like notes and paperwork? Created by Vals AI. Higher is better. | 88.89% | — |
ZeroBench (tools, pass@5)Visual reasoning — percentage of 100 visual problems solved at least once in five attempts with tools | 46% | — |
SimpleVQA (with tools)Visual reasoning — accuracy on 2,024 English and Chinese visual questions with tools | 73.3% | — |
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. | 76.3% | — |
MMMU-Pro · standard and vision meanMultimodal reasoning — average across the standard and vision sets | — | 74.1% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 81.6% |
GraphWalks BFS (<128K)Long context — breadth-first traversal accuracy for inputs shorter than 128K tokens | — | 73.4% |
GraphWalks parents (<128K)Long context — parent-node retrieval accuracy for inputs shorter than 128K tokens | — | 64.3% |
OpenAI MRCR (2 needles) · 128KLong context — retrieval of two matching turns in the original MRCR evaluation | — | 84.3% |
OpenAI MRCR (2 needles) · 256KLong context — retrieval of two matching turns in the original MRCR evaluation | — | 58.8% |
| Overview | ||
| Company | Meta | OpenAI |
| Release date | Jul 9 2026 | Aug 7 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Muse Spark 1.1vsClaude Fable 5.2GPT-5 minivsClaude Fable 5.2Muse Spark 1.1vsGemini 4 NeonGPT-5 minivsGemini 4 NeonMuse Spark 1.1vsGrok 4.7GPT-5 minivsGrok 4.7Muse Spark 1.1vsDeepSeek-V4.1-Flash-1017GPT-5 minivsDeepSeek-V4.1-Flash-1017Muse Spark 1.1vsMistral Large 4GPT-5 minivsMistral Large 4Muse Spark 1.1vsKimi K3.1 ProGPT-5 minivsKimi K3.1 ProFrequently asked questions
Muse Spark 1.1 leads GPT-5 mini on 1 of the 2 benchmarks they both report (ProgramBench, CharXiv Reasoning). GPT-5 mini is cheaper on both input and output: $0.25 vs $1.25 per million input tokens, and $2.00 vs $4.25 per million output tokens. GPT-5 mini shipped 336 days before Muse Spark 1.1, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Muse Spark 1.1) vs 400k (GPT-5 mini).
On ProgramBench, both models score 0%. On CharXiv Reasoning · with tools, Muse Spark 1.1 leads at 88.4% vs GPT-5 mini at 75.5%.