Compare AI models
| Specifications | ||
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 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. | $0.22 | $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. | $0.66 | $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. | $0.007 | $0.10 |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.0108Relace | $1.00OpenAI |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $0.132StreamLake | $5.00OpenAI |
| Benchmarks | ||
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% | 65% |
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. | 25.1% | 36.2% |
Auto-review circumvention (Internal)Safety-review circumvention — OpenAI's internal safety check on how often a model finds ways around its own automated review — the guardrail that inspects what it is about to do. This one counts failures, so lower is better and zero is the goal. | — | 0% |
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. | 79% | — |
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. | — | 75.2% |
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. | 82.7% | — |
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. | — | 57.1% |
Toolathlon-VerifiedPersonal tool use — Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | 70.3% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 73.2% | — |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 76.7% | — |
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. | 34.8% | — |
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. | 61.4% | — |
OSWorld 2.0Agentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.0 is a harder, refreshed task set. Higher is better. | — | 71.4% |
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. | — | 32% |
| Overview | ||
| Company | DeepSeek | OpenAI |
| Release date | Jul 31 2026 | Sep 29 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-Flash-0731vsClaude Sonnet 5.5GPT-6.1 SolvsClaude Sonnet 5.5DeepSeek-V4-Flash-0731vsGemini 4 ArgonGPT-6.1 SolvsGemini 4 ArgonDeepSeek-V4-Flash-0731vsMuse Spark 1.3GPT-6.1 SolvsMuse Spark 1.3DeepSeek-V4-Flash-0731vsGrok 4.7GPT-6.1 SolvsGrok 4.7DeepSeek-V4-Flash-0731vsMistral Medium 3.5GPT-6.1 SolvsMistral Medium 3.5DeepSeek-V4-Flash-0731vsKimi K3GPT-6.1 SolvsKimi K3Frequently asked questions
GPT-6.1 Sol leads DeepSeek-V4-Flash-0731 on 2 of the 2 benchmarks they both report (BullshitBench v2, AutomationBench). DeepSeek-V4-Flash-0731 is cheaper on both input and output: $0.22 vs $2.00 per million input tokens, and $0.66 vs $10.00 per million output tokens. Figures are base-tier rates. DeepSeek-V4-Flash-0731 shipped 60 days before GPT-6.1 Sol, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Flash-0731 is open weight, while GPT-6.1 Sol is closed.
On BullshitBench v2, GPT-6.1 Sol leads at 65% vs DeepSeek-V4-Flash-0731 at 39%. On AutomationBench, GPT-6.1 Sol leads at 36.2% vs DeepSeek-V4-Flash-0731 at 25.1%.