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 |
| 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 | $3.75 |
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. | — | $0.375Google |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $1.875Google |
| $3,600Anthropic list price | $338Google 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. | — | 39% |
Gray Swan IPI · k = 1Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | — | 7.3% |
Gray Swan IPI · k = 10Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | — | 32.2% |
Gray Swan IPI · k = 15Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | — | 37.3% |
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. | — | 0.5% |
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. | — | 58.7% |
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. | — | 49% |
FrontierCode v1.1 (Main) · main splitAgentic coding — A set of very hard, frontier-difficulty coding tasks an AI agent has to complete end to end. The score is the share of tasks in the main split it solves. Higher is better. | — | 34.4% |
MLE-BenchML engineering — Can the AI do the work of a machine-learning engineer? It competes in real Kaggle competitions — building, training, and tuning models end to end — and the score reflects how well it places. Higher is better. | — | 63.9% |
Terminal-Bench 3.0Agentic terminal coding — command-line task completion (v3.0, much harder task set) | — | 5.4% |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 78% |
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% | — |
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. | — | 68% |
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 (Verified)Multidisciplinary reasoning — The re-checked edition of Humanity's Last Exam: the same extremely hard expert questions, minus the ones found to be flawed or wrongly answered. Scores on it run lower than on the original exam, so read the two as separate tests rather than a before-and-after. Higher is better. | — | 51.2% |
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. | — | 60.4% |
BioMysteryBench · hardBiology — Real unsolved-style biology puzzles — the AI has to reason its way to an answer the way a research biologist would. The “hard” split contains the toughest cases. Higher is better. | — | 41.2% |
BioMysteryBench · human solvedBiology — Real biology puzzles that human experts have managed to crack — can the AI reach the same answers? Higher is better. | — | 80.6% |
LAB-Bench 2Biology — Everyday tasks from a working biology lab — reading protocols, interpreting figures and sequence data, and answering the practical questions a researcher hits at the bench. Higher is better. | — | 76.1% |
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. | — | 83% |
Agent's Last Exam · pass@1Agentic computer use — A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. | — | 24.2% |
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. | — | 17% |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | — | 52 |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | — | 1421 |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 85.2% |
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. | — | 89.4% |
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. | — | 22% |
LVBenchVideo understanding — Can the AI follow a very long video — up to an hour — and answer questions that need details from far apart in it? Higher is better. | — | 84.2% |
MRCR v2 (8-needle) · 128k averageLong context — Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. | — | 91.8% |
MRCR v2 (8-needle) · 1M pointwiseLong context — Tests whether the AI can find specific details buried inside an enormous document (around 1 million tokens — many books). Higher is better. | — | 54% |
threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. | — | 1340 |
| Overview | ||
| Company | Anthropic | |
| Release date | Nov 9 2026 | Jul 21 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Mythos 5.2vsGPT-6.1 TerraGemini 3.6 FlashvsGPT-6.1 TerraClaude Mythos 5.2vsMuse EmberGemini 3.6 FlashvsMuse EmberClaude Mythos 5.2vsGrok 4.7Gemini 3.6 FlashvsGrok 4.7Claude Mythos 5.2vsDeepSeek-V4.1-Flash-1017Gemini 3.6 FlashvsDeepSeek-V4.1-Flash-1017Claude Mythos 5.2vsMistral Large 4Gemini 3.6 FlashvsMistral Large 4Claude Mythos 5.2vsKimi K3.1 ProGemini 3.6 FlashvsKimi K3.1 ProFrequently asked questions
Claude Mythos 5.2 and Gemini 3.6 Flash don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Gemini 3.6 Flash is cheaper on both input and output: $0.75 vs $8.00 per million input tokens, and $3.75 vs $40.00 per million output tokens. Claude Mythos 5.2 requires organization verification. Gemini 3.6 Flash shipped 111 days before Claude Mythos 5.2, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Mythos 5.2) vs 1M (Gemini 3.6 Flash).
Direct benchmark comparisons are unavailable — Claude Mythos 5.2 and Gemini 3.6 Flash don't publish scores on any of the same benchmarks.