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 | 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. | $1.25 | $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. | $10.00 | $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. | $0.125 | $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. | $0.625Google AI Studio | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $5.00Google AI Studio | — |
| $750Google 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. | 84% | 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. | 20% | — |
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. | 63.8% | — |
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% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 70.4% | — |
Aider Polyglot (diff)Coding — editing code in six languages using the diff edit format | 68.6% | — |
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% |
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. | 18.8% | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 92% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 86.7% | — |
Vals Science Index v1Scientific reasoning — Vals AI’s composite accuracy across three scientific reasoning evaluations | — | 68.4% |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 52.9% | — |
Agents’ Last Exam v1.1Agentic computer use — averaged rubric score on the 122-task v1.1 suite of long-horizon professional workflows | — | 78.3% |
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 v2 (OpenAI Internal)Knowledge work — OpenAI’s internal score on multistep professional assignments drawn from consulting, finance, and design projects | — | 50.4% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 81.7% | — |
AA-3DCommunity preference (interactive 3D) — blind human preferences between paired interactive 3D experiences built from the same prompt | — | 1318 |
| Overview | ||
| Company | OpenAI | |
| Release date | Mar 25 2025 | Nov 17 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Gemini 2.5 ProvsClaude Fable 5.2GPT-6.2 AstravsClaude Fable 5.2Gemini 2.5 ProvsMuse EmberGPT-6.2 AstravsMuse EmberGemini 2.5 ProvsGrok 4.7GPT-6.2 AstravsGrok 4.7Gemini 2.5 ProvsDeepSeek-V4.1-Flash-1017GPT-6.2 AstravsDeepSeek-V4.1-Flash-1017Gemini 2.5 ProvsMistral Large 4GPT-6.2 AstravsMistral Large 4Gemini 2.5 ProvsKimi K3.1 ProGPT-6.2 AstravsKimi K3.1 ProFrequently asked questions
GPT-6.2 Astra leads Gemini 2.5 Pro on 1 of the 1 benchmark they both report (GPQA Diamond). Gemini 2.5 Pro is cheaper on both input and output: $1.25 vs $8.00 per million input tokens, and $10.00 vs $40.00 per million output tokens. Figures are base-tier rates. Gemini 2.5 Pro shipped 602 days before GPT-6.2 Astra, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 2.5 Pro) vs 1.05M (GPT-6.2 Astra).
On GPQA Diamond, GPT-6.2 Astra leads at 97% vs Gemini 2.5 Pro at 84%.