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. | 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. | — | 79% |
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% |
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. | 58.7% | — |
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% |
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. | 86.7% | — |
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% |
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% |
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% |
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 | Anthropic | Meta |
| Release date | Aug 9 2023 | Oct 12 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Instant 1.2vsGPT-6.1 SolMuse Wonder FullvsGPT-6.1 SolClaude Instant 1.2vsGemini 4 ArgonMuse Wonder FullvsGemini 4 ArgonClaude Instant 1.2vsGrok 4.7Muse Wonder FullvsGrok 4.7Claude Instant 1.2vsDeepSeek-V4.1-Flash-1017Muse Wonder FullvsDeepSeek-V4.1-Flash-1017Claude Instant 1.2vsMistral Large 4Muse Wonder FullvsMistral Large 4Claude Instant 1.2vsKimi K3Muse Wonder FullvsKimi K3Frequently asked questions
Claude Instant 1.2 and Muse Wonder Full don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude Instant 1.2 shipped 1160 days before Muse Wonder Full, so benchmark comparisons should account for the intervening progress.
Context windows are 100k (Claude Instant 1.2) vs 1M (Muse Wonder Full).
Direct benchmark comparisons are unavailable — Claude Instant 1.2 and Muse Wonder Full don't publish scores on any of the same benchmarks.