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 | 400k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $8.00Verified organizations only | $0.75 |
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. | $40.00 | $4.50 |
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. | $0.20 | $0.075 |
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.375OpenAI |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $2.25OpenAI |
| $3,600Anthropic list price | $375OpenAI list price | |
| These models have no shared benchmark scores. | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 32% |
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. | — | 0% |
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. | — | 54.4% |
Supabase Evals · with skillsSupabase coding — Supabase's own open benchmark: a coding agent is dropped into a real Supabase project and asked to do real work — set up a schema, fix a broken security policy, debug an Edge Function — and every run is checked against a live Supabase stack. This is the headline number, where the agent has Supabase's own skills loaded, as most people building on Supabase would. The score is the share of scenarios it got right. Higher is better. | — | 65.2% |
Supabase Evals · no skillsSupabase coding — The same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better. | — | 55.1% |
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. | — | 60% |
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. | 75.3% | — |
De novo binder design (24 hr)Protein design — de novo protein binder design within a 24-hour budget, as reported by Anthropic | 85.1% | — |
MCP Atlas · original harnessMulti-step tool use — pass rate under the original tool-use harness, before Scale changed the judge and retry handling in April 2026 | — | 57.7% |
ToolathlonGeneral tool use — Tests how well the AI uses everyday real-world tools and apps to get things done. Higher is better. | — | 42.9% |
BU BenchBrowser agent — Can the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | — | 36% |
CyScenarioBenchCybersecurity — multi-step cybersecurity scenarios; each lab runs its own unique task set, so scores from different labs do not compare | 76.3% | — |
CVE RediscoveryCybersecurity — Anthropic internal evaluation: share of 1,829 published CVEs a model finds on its own from a snapshot of the project before the fix | 89.6% | — |
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. | — | 28.2% |
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. | — | 41.5% |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 18.9% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 88% |
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. | — | 72.1% |
MMMU-Pro · with toolsMultimodal reasoning — multimodal understanding and reasoning with access to tools | — | 78% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 76.6% |
GraphWalks BFS (<128K)Long context — breadth-first traversal accuracy for inputs shorter than 128K tokens | — | 76.3% |
GraphWalks parents (<128K)Long context — parent-node retrieval accuracy for inputs shorter than 128K tokens | — | 71.5% |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Nov 9 2026 | Mar 17 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Mythos 5.2vsGemini 4 CarbonGPT-5.4 minivsGemini 4 CarbonClaude Mythos 5.2vsMuse EmberGPT-5.4 minivsMuse EmberClaude Mythos 5.2vsGrok 4.7GPT-5.4 minivsGrok 4.7Claude Mythos 5.2vsDeepSeek-V4.1-Flash-1017GPT-5.4 minivsDeepSeek-V4.1-Flash-1017Claude Mythos 5.2vsMistral Large 4GPT-5.4 minivsMistral Large 4Claude Mythos 5.2vsKimi K3.1 ProGPT-5.4 minivsKimi K3.1 ProFrequently asked questions
Claude Mythos 5.2 and GPT-5.4 mini don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GPT-5.4 mini is cheaper on both input and output: $0.75 vs $8.00 per million input tokens, and $4.50 vs $40.00 per million output tokens. Claude Mythos 5.2 requires organization verification. GPT-5.4 mini shipped 237 days before Claude Mythos 5.2, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Mythos 5.2) vs 400k (GPT-5.4 mini).
Direct benchmark comparisons are unavailable — Claude Mythos 5.2 and GPT-5.4 mini don't publish scores on any of the same benchmarks.