Compare AI models
| Specifications | ||
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 | 1.05M |
| 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. | — | $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. | — | $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. | — | $0.10 |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $1.25Meta | $1.00OpenAI |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $4.25Meta | $5.00OpenAI |
| Benchmarks | ||
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. | 75.4% | 75.2% |
OSWorld 2.0Agentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.0 is a harder, refreshed task set. Higher is better. | 66.9% | 71.4% |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | 49.4% | 36.2% |
CheatBenchCheating rate — Measures how often AI agents try to cheat on difficult assignments, such as reading hidden answers, copying work or manipulating grading. The overall score gives equal weight to ten categories; the sycophancy category measures how far an agent shifts its beliefs toward a user's stated views. Scores describe each model in its tested agent setup, and task success is measured separately. Lower is better. | 39% | — |
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. | — | 65% |
Auto-review circumvention (Internal)Safety-review circumvention — OpenAI's internal safety check on how often a model finds ways around its own automated review — the guardrail that inspects what it is about to do. This one counts failures, so lower is better and zero is the goal. | — | 0% |
CursorBench 4.0Agentic coding — Cursor's own test of coding agents on ambiguous, multi-file tasks taken from real Cursor sessions — editing, refactoring, investigating a codebase, understanding what the user meant, managing jobs and following a design. Cursor runs each model at several reasoning efforts; each release here carries the score of its best listed effort. Scores aren't comparable with earlier CursorBench versions. Higher is better. | 41.6% | — |
SWEAtlas CodeBase QnACodebase understanding — Questions about how an unfamiliar codebase actually works — where something is handled, what a change would touch — answered by reading the repository rather than editing it. Tests understanding rather than patch-writing. Higher is better. | 59.4% | — |
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. | 88.8% | — |
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. | — | 57.1% |
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. | 64.9% | — |
DeepSearchQAAgentic browsing — Questions that cannot be answered from one page: the AI has to search the web, follow the trail across several sources, and put the pieces together into an answer. Higher is better. | 89.4% | — |
Agentic IF Index (Internal)Instruction following — Meta's internal measure of whether a model keeps following the instructions it was given while working as an agent — over a long run of tool calls, not just in a single reply. Higher is better. | 57.8% | — |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 1754 | — |
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. | — | 32% |
MRCR · 256k-512kLong context — Tests whether the AI can find specific details buried inside a very long document, here across inputs of roughly 256k to 512k tokens — several books' worth of text. Higher is better. | 98.5% | — |
MRCR · 512k-1MLong context — The same buried-detail retrieval test run on even longer inputs, from roughly 512k up to a million tokens. Scores usually slip as the document grows, so read it against the shorter span above. Higher is better. | 98.1% | — |
threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. | 1448 | — |
| Overview | ||
| Company | Meta | OpenAI |
| Release date | Sep 2 2026 | Sep 29 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Muse Spark 1.3vsClaude Sonnet 5.5GPT-6.1 SolvsClaude Sonnet 5.5Muse Spark 1.3vsGemini 4 ArgonGPT-6.1 SolvsGemini 4 ArgonMuse Spark 1.3vsGrok 4.7GPT-6.1 SolvsGrok 4.7Muse Spark 1.3vsDeepSeek-V4.1-FlashGPT-6.1 SolvsDeepSeek-V4.1-FlashMuse Spark 1.3vsMistral Medium 3.5GPT-6.1 SolvsMistral Medium 3.5Muse Spark 1.3vsKimi K3GPT-6.1 SolvsKimi K3Frequently asked questions
Muse Spark 1.3 leads GPT-6.1 Sol on 2 of the 3 benchmarks they both report (DeepSWE 1.1, OSWorld 2.0, AutomationBench). Only GPT-6.1 Sol has a verified first-party API price: $2.00 per million input tokens and $10.00 per million output tokens. No pay-as-you-go API rate is tracked for Muse Spark 1.3. Muse Spark 1.3 shipped 27 days before GPT-6.1 Sol, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Muse Spark 1.3) vs 1.05M (GPT-6.1 Sol).
On DeepSWE 1.1, Muse Spark 1.3 leads at 75.4% vs GPT-6.1 Sol at 75.2%. On OSWorld 2.0, GPT-6.1 Sol leads at 71.4% vs Muse Spark 1.3 at 66.9%. On AutomationBench, Muse Spark 1.3 leads at 49.4% vs GPT-6.1 Sol at 36.2%.