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. | 200k | 1.05M |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $5.00 | $8.00 |
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. | $25.00 | $40.00 |
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. | $0.50 | $0.40 |
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. | $5.00Amazon Bedrock | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $25.00Amazon Bedrock | — |
| $2,250Anthropic list price | $3,600OpenAI list price | |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 87% | 97% |
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. | 90% | — |
Blocker Deception (OpenAI) · without Codex promptBlocker disclosure — share of coding trials where the model omitted or misrepresented an obstacle without the Codex developer prompt | — | 22.28% |
Blocker Deception (OpenAI) · with Codex promptBlocker disclosure — share of coding trials where the model omitted or misrepresented an obstacle with the Codex developer prompt | — | 8.04% |
Simulated Workplace Tasks (OpenAI)High-severity improper actions — share of scored simulated workplace tasks with a high-severity improper action | — | 0.64% |
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. | 80.9% | — |
FrontierCode 2.0Agentic coding — whether a model’s code changes to open-source repositories would be merged by their maintainers (version 2.0); separate from FrontierCode v1.1 scores | — | 44.2% |
BenchCAD 2.1 CoreCAD programming — partial-credit score for modeling hardware designs in the held-out Core evaluation | — | 82.5% |
SecureSWESecure code generation — OpenAI’s internal evaluation of writing code that is both functional and secure | — | 65.7% |
PatchBenchSecurity patching — security patches that fix vulnerabilities while preserving intended behavior | — | 79.7% |
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. | 59.8% | — |
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. | — | 77.1% |
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 | 62.3% | — |
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. | 30.8% | — |
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. | 43.4% | — |
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. | 37.64% | — |
Vals Science Index v1Scientific reasoning — Vals AI’s composite accuracy across three scientific reasoning evaluations | — | 68.4% |
Agents’ Last Exam v1.1Agentic computer use — averaged rubric score on the 122-task v1.1 suite of long-horizon professional workflows | — | 78.3% |
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. | 66.3% | — |
AutomationBench 1.0.6Business workflows — end-to-end business workflow automation on the version 1.0.6 task set | — | 52.4% |
LifeValEveryday tasks — OpenAI’s rubric score for completing practical everyday tasks tailored to a person’s needs | — | 86.1% |
AA-AnalystAgent (pass^5)Financial research — share of quantitative questions about real spreadsheets and reports answered correctly on all five independent attempts | — | 62.5% |
Harvey LAB-AA v1.1Agentic legal work — full-credit rate on legal assignments, requiring every grading criterion to be met without material hallucinations | — | 15% |
HealthBench Professional · OpenAI grading, rawHealth — unadjusted physician-rubric score using the official OpenAI grading procedure | — | 66% |
HealthBench Professional · OpenAI grading, length-adjustedHealth — official OpenAI grading with the response-length penalty applied | — | 66.3% |
MentalHealthBenchMental health — overall clinician-rubric score on mental health conversations | — | 53.3% |
AA Intelligence Index v5.0.1Overall intelligence — Artificial Analysis’s version 5.0.1 composite across nine evaluations of knowledge work, coding, science, and general knowledge | — | 62.1 |
GDPval-AAKnowledge work — Measures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. | 1416 | — |
GDPval v2 (OpenAI Internal)Knowledge work — OpenAI’s internal score on multistep professional assignments drawn from consulting, finance, and design projects | — | 50.4% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 70.6% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 80.7% | — |
AA-3DCommunity preference (interactive 3D) — blind human preferences between paired interactive 3D experiences built from the same prompt | — | 1318 |
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. | 1138 | — |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Nov 24 2025 | Nov 17 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Opus 4.5vsGemini 4 HydrogenGPT-6.2 AstravsGemini 4 HydrogenClaude Opus 4.5vsMuse EmberGPT-6.2 AstravsMuse EmberClaude Opus 4.5vsGrok 4.7GPT-6.2 AstravsGrok 4.7Claude Opus 4.5vsDeepSeek-V4.1-Flash-1017GPT-6.2 AstravsDeepSeek-V4.1-Flash-1017Claude Opus 4.5vsMistral Large 4GPT-6.2 AstravsMistral Large 4Claude Opus 4.5vsKimi K3.1 ProGPT-6.2 AstravsKimi K3.1 ProFrequently asked questions
GPT-6.2 Astra leads Claude Opus 4.5 on 1 of the 1 benchmark they both report (GPQA Diamond). Claude Opus 4.5 is cheaper on both input and output: $5.00 vs $8.00 per million input tokens, and $25.00 vs $40.00 per million output tokens. Figures are base-tier rates. Claude Opus 4.5 shipped 358 days before GPT-6.2 Astra, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude Opus 4.5) vs 1.05M (GPT-6.2 Astra).
On GPQA Diamond, GPT-6.2 Astra leads at 97% vs Claude Opus 4.5 at 87%.