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. | $8.00Verified organizations only | $2.00 |
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. | $40.00 | $10.00 |
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. | $0.20 | $0.10 |
| $3,600Anthropic list price | $900OpenAI list price | |
| Benchmarks | ||
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% | 68% |
Blocker Deception (OpenAI) · without Codex promptBlocker disclosure — share of coding trials where the model omitted or misrepresented an obstacle without the Codex developer prompt | — | 24.08% |
Blocker Deception (OpenAI) · with Codex promptBlocker disclosure — share of coding trials where the model omitted or misrepresented an obstacle with the Codex developer prompt | — | 8.88% |
Simulated Workplace Tasks (OpenAI)High-severity improper actions — share of scored simulated workplace tasks with a high-severity improper action | — | 0.71% |
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 | — | 43.8% |
BenchCAD 2.1 CoreCAD programming — partial-credit score for modeling hardware designs in the held-out Core evaluation | — | 73.1% |
SecureSWESecure code generation — OpenAI’s internal evaluation of writing code that is both functional and secure | — | 55.6% |
PatchBenchSecurity patching — security patches that fix vulnerabilities while preserving intended behavior | — | 75.6% |
De novo binder design (24 hr)Protein design — de novo protein binder design within a 24-hour budget, as reported by Anthropic | 85.1% | — |
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% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 96% |
Vals Science Index v1Scientific reasoning — Vals AI’s composite accuracy across three scientific reasoning evaluations | — | 58.5% |
Agents’ Last Exam v1.1Agentic computer use — averaged rubric score on the 122-task v1.1 suite of long-horizon professional workflows | — | 73% |
AutomationBench 1.0.6Business workflows — end-to-end business workflow automation on the version 1.0.6 task set | — | 41.1% |
LifeValEveryday tasks — OpenAI’s rubric score for completing practical everyday tasks tailored to a person’s needs | — | 83.8% |
Harvey LAB-AA v1.1Agentic legal work — full-credit rate on legal assignments, requiring every grading criterion to be met without material hallucinations | — | 11.1% |
HealthBench Professional · OpenAI grading, rawHealth — unadjusted physician-rubric score using the official OpenAI grading procedure | — | 65.5% |
HealthBench Professional · OpenAI grading, length-adjustedHealth — official OpenAI grading with the response-length penalty applied | — | 65.9% |
MentalHealthBenchMental health — overall clinician-rubric score on mental health conversations | — | 50.9% |
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 | — | 57.3 |
GDPval v2 (OpenAI Internal)Knowledge work — OpenAI’s internal score on multistep professional assignments drawn from consulting, finance, and design projects | — | 46.9% |
AA-3DCommunity preference (interactive 3D) — blind human preferences between paired interactive 3D experiences built from the same prompt | — | 1259 |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Nov 9 2026 | Nov 17 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Claude Mythos 5.2vsGemini 4 HydrogenGPT-6.2 SolvsGemini 4 HydrogenClaude Mythos 5.2vsMuse EmberGPT-6.2 SolvsMuse EmberClaude Mythos 5.2vsGrok 4.7GPT-6.2 SolvsGrok 4.7Claude Mythos 5.2vsDeepSeek-V4.1-Flash-1017GPT-6.2 SolvsDeepSeek-V4.1-Flash-1017Claude Mythos 5.2vsMistral Large 4GPT-6.2 SolvsMistral Large 4Claude Mythos 5.2vsKimi K3.1 ProGPT-6.2 SolvsKimi K3.1 ProFrequently asked questions
Claude Mythos 5.2 leads GPT-6.2 Sol on 1 of the 1 benchmark they both report (Terminal-Bench-Science 0.1). GPT-6.2 Sol is cheaper on both input and output: $2.00 vs $8.00 per million input tokens, and $10.00 vs $40.00 per million output tokens. Figures are base-tier rates. Claude Mythos 5.2 requires organization verification. Claude Mythos 5.2 shipped 8 days before GPT-6.2 Sol, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Mythos 5.2) vs 1.05M (GPT-6.2 Sol).
On Terminal-Bench-Science 0.1, Claude Mythos 5.2 leads at 75.3% vs GPT-6.2 Sol at 68%.