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 | 200k |
| Benchmarks | ||
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 93.9% | 49.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 94.5% | 77.2% |
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 77.8% | — |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 87.3% | — |
SWE-Bench MultimodalMultimodal coding — Real bug reports that arrive with pictures attached — a screenshot, a mockup, a page rendering wrongly — so the AI has to read the image as well as the code to work out what to fix. Higher is better. | 59% | — |
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. | — | 97.6% |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | 82% | — |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 83.1% | — |
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. | 56.8% | — |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 64.7% | — |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | — | 97.9% |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | — | 80.6 |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | — | 13.8% |
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. | — | 86.9% |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | — | 92% |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 79.6% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 86.1% | — |
CharXiv Reasoning · with toolsChart reasoning — The same chart-and-figure reasoning test, run with the AI allowed to use tools — writing code to inspect the image, for instance — rather than reading the chart unaided. Scores run higher than the unaided version, so read the two as separate tests. Higher is better. | 93.2% | — |
GraphWalks BFS (256K–1M)Long context — breadth-first search F1 on the 200 GraphWalks problems with 256K to 1M tokens of context | 80% | — |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Apr 7 2026 | Jan 31 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Mythos PreviewvsGemini 4 Carbono3-mini-highvsGemini 4 CarbonClaude Mythos PreviewvsMuse Embero3-mini-highvsMuse EmberClaude Mythos PreviewvsGrok 4.7o3-mini-highvsGrok 4.7Claude Mythos PreviewvsDeepSeek-V4.1-Flash-1017o3-mini-highvsDeepSeek-V4.1-Flash-1017Claude Mythos PreviewvsMistral Large 4o3-mini-highvsMistral Large 4Claude Mythos PreviewvsKimi K3.1 Proo3-mini-highvsKimi K3.1 ProFrequently asked questions
Claude Mythos Preview leads o3-mini-high on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). o3-mini-high shipped 431 days before Claude Mythos Preview, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Mythos Preview) vs 200k (o3-mini-high).
On SWE-Bench Verified, Claude Mythos Preview leads at 93.9% vs o3-mini-high at 49.3%. On GPQA Diamond, Claude Mythos Preview leads at 94.5% vs o3-mini-high at 77.2%.