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 |
| 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 |
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 |
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 |
| — | $45.00Meta list price | |
| 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. | 65.2% | 40.9% |
AA Intelligence Index v5.0Overall intelligence — Artificial Analysis composite intelligence index, version 5.0 with tools; separate from earlier index editions | 59 | 36 |
Gray Swan IPI · k = 15Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | 0% | — |
SWE-sweepAgentic coding — subtask-weighted reward for software engineering with the mini-swe-agent harness | 9.6% | — |
FrontierSWE V2Ultra-long-horizon coding — Engineering problems that would occupy a person for days: systems implementation, performance work, scientific computing and AI research, with up to twenty hours per task. Partial credit is awarded, because finishing one outright is still rare. Higher is better. | 61.2% | — |
FrontierCode 2.0Agentic coding — whether a model’s code changes to open-source repositories would be merged by their maintainers (version 2.0); separate from FrontierCode v1.1 scores | 41.1% | — |
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 |
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. | 64.8% | — |
RiemannBenchAdvanced mathematics — mathematical problem-solving evaluation published by Surge | 80% | — |
Agents’ Last Exam v1.1Agentic computer use — averaged rubric score on the 122-task October 17, 2026 v1.1 set, using ALE-Claw with a five-hour limit; separate from earlier ALE scores | 77.4% | — |
CWE-bench v1Security patching — Collinear AI’s programmatically graded security-patch pass@1 rate; separate from exploit-generation benchmarks | 71% | — |
ExploitGym (causal pass rate) · 10-hour budgetCybersecurity — share of tasks producing a verified exploit of the intended vulnerability, with mitigations off; not a count of solved instances | 54.8% | — |
ExploitGym (causal pass rate) · 6-hour budgetCybersecurity — share of tasks producing a verified exploit of the intended vulnerability, with mitigations off; not a count of solved instances | 53.5% | — |
SEC-bench Pro (JavaScript)Vulnerability discovery — pass@1 on the 183-task May 2026 JavaScript-engine split, averaged over three trials with the Antigravity harness | 88.2% | — |
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. | 81.5% | — |
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. | 53.9% | — |
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% |
Vals Index v2.2Professional work — Vals AI composite evaluation of professional tasks, version 2.2 | 70.4% | — |
Vending-Bench 2 (USD)Business simulation — ending bank balance in US dollars in Andon Labs’ vending-business simulation; higher is better | 16484 | — |
AA-Briefcase v1.1Knowledge work — Artificial Analysis agentic office-work eval (Elo, v1.1 rating fit) | 1611 | — |
AA-Briefcase v1.1 (rubric)Knowledge work — Artificial Analysis agentic office-work eval, v1.1 rubric score; separate from the Elo rating | 61.8% | — |
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. | 72.5% | — |
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% |
Blueprint-Bench 2Spatial reasoning — Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better. | 58.6% | — |
GraphWalks BFS (256K–1M)Long context — breadth-first search F1 on the 200 GraphWalks problems with 256K to 1M tokens of context | 96.2% | — |
| Overview | ||
| Company | Meta | |
| Release date | Oct 28 2026 | Nov 9 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Gemini 4 CarbonvsClaude Fable 5.2Muse EmbervsClaude Fable 5.2Gemini 4 CarbonvsGPT-6.1 TerraMuse EmbervsGPT-6.1 TerraGemini 4 CarbonvsGrok 4.7Muse EmbervsGrok 4.7Gemini 4 CarbonvsDeepSeek-V4.1-Flash-1017Muse EmbervsDeepSeek-V4.1-Flash-1017Gemini 4 CarbonvsMistral Large 4Muse EmbervsMistral Large 4Gemini 4 CarbonvsKimi K3.1 ProMuse EmbervsKimi K3.1 ProFrequently asked questions
Gemini 4 Carbon leads Muse Ember on 2 of the 2 benchmarks they both report (Terminal-Bench 4.0, AA Intelligence Index v5.0). Only Muse Ember has a verified first-party price for an available API: $0.10 per million input tokens and $0.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for Gemini 4 Carbon. Gemini 4 Carbon shipped 12 days before Muse Ember, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On Terminal-Bench 4.0, Gemini 4 Carbon leads at 65.2% vs Muse Ember at 40.9%. On AA Intelligence Index v5.0, Gemini 4 Carbon leads at 59 vs Muse Ember at 36.