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. | 100k | 1M |
These models have no shared benchmark scores. | ||
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. | — | 78.8% |
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. | — | 53.1% |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 71.2% | — |
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. | — | 70.5% |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 78.5% | — |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 88% | — |
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. | — | 39.1% |
Finance Agent v2Agentic financial analysis — Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | — | 56.6% |
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. | — | 60.5% |
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. | — | 30.8% |
| Overview | ||
| Company | Anthropic | Meta |
| Release date | Jul 11 2023 | Oct 12 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude 2vsGPT-6.1 SolMuse WondervsGPT-6.1 SolClaude 2vsGemini 4 ArgonMuse WondervsGemini 4 ArgonClaude 2vsGrok 4.7Muse WondervsGrok 4.7Claude 2vsDeepSeek-V4.1-FlashMuse WondervsDeepSeek-V4.1-FlashClaude 2vsMistral Large 4Muse WondervsMistral Large 4Claude 2vsKimi K3Muse WondervsKimi K3Frequently asked questions
Claude 2 and Muse Wonder don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude 2 shipped 1189 days before Muse Wonder, so benchmark comparisons should account for the intervening progress.
Context windows are 100k (Claude 2) vs 1M (Muse Wonder).
Direct benchmark comparisons are unavailable — Claude 2 and Muse Wonder don't publish scores on any of the same benchmarks.