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 | 1M |
| 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. | 79% | 75.7% |
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. | 57.1% | 48.5% |
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. | 75.3% | 68.5% |
HealthBench ProfessionalHealth — Realistic health conversations graded against detailed rubrics written by physicians — can the AI respond the way a careful medical professional would? Higher is better. | 62.3% | 60% |
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. | 8.5% | — |
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. | 57.5% | — |
APEX-AgentsExpert agentic work — expert-level agentic work tasks (AI Productivity Index) | — | 72.1% |
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. | — | 51.7% |
BioMysteryBench · human solvedBiology — Real biology puzzles that human experts have managed to crack — can the AI reach the same answers? Higher is better. | — | 85% |
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 | — | 46.7% |
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. | 45.4% | — |
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. | — | 72.5% |
Finance Agent v2Agentic financial analysis — Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 59.1% | — |
AA-Briefcase v1.1Knowledge work — Artificial Analysis agentic office-work eval (Elo, v1.1 rating fit) | — | 1686 |
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. | — | 54.2% |
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. | 33.2% | — |
| Overview | ||
| Company | Meta | Qwen |
| Release date | Oct 12 2026 | Nov 11 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Muse Wonder FullvsClaude Fable 5.2Qwen4-MaxvsClaude Fable 5.2Muse Wonder FullvsGPT-6.1 TerraQwen4-MaxvsGPT-6.1 TerraMuse Wonder FullvsGemini 4 HydrogenQwen4-MaxvsGemini 4 HydrogenMuse Wonder FullvsGrok 4.7Qwen4-MaxvsGrok 4.7Muse Wonder FullvsDeepSeek-V4.1-Flash-1017Qwen4-MaxvsDeepSeek-V4.1-Flash-1017Muse Wonder FullvsMistral Large 4Qwen4-MaxvsMistral Large 4Frequently asked questions
Muse Wonder Full leads Qwen4-Max on 4 of the 4 benchmarks they both report (DeepSWE 1.1, Terminal-Bench 4.0, JobBench, HealthBench Professional). Muse Wonder Full shipped 30 days before Qwen4-Max, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Muse Wonder Full) vs 1M (Qwen4-Max).
On DeepSWE 1.1, Muse Wonder Full leads at 79% vs Qwen4-Max at 75.7%. On Terminal-Bench 4.0, Muse Wonder Full leads at 57.1% vs Qwen4-Max at 48.5%. On JobBench, Muse Wonder Full leads at 75.3% vs Qwen4-Max at 68.5%. On HealthBench Professional, Muse Wonder Full leads at 62.3% vs Qwen4-Max at 60%.