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. | 1M | — |
| 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. | $0.10 | $0.66 |
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. | $0.50 | $1.98 |
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. | $0.01 | $0.022 |
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. | — | $0.19Wafer |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $1.98DeepSeek |
| Benchmarks | ||
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. | 45.9% | 42.7% |
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. | 57.4% | 60% |
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. | — | 35% |
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. | — | 80.6% |
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. | 46.4% | — |
Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. | 39.2% | — |
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. | — | 87.9% |
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. | — | 74.1% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 83.4% |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | — | 83.3% |
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. | — | 61.3% |
OSWorld 2.1 (offline)Agentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.1, in its offline setting. Scores are not comparable with version 2.0. Higher is better. | 72.4% | — |
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. | — | 31.8% |
GDPval-AA v2.1Knowledge work — economically valuable knowledge work (v2.1, Crowd-BT Elo fit) | 1620 | — |
AA-Briefcase v1.1Knowledge work — Artificial Analysis agentic office-work eval (Elo, v1.1 rating fit) | 1578 | — |
Chartography · no toolsChart tasks — The same chart-centred test with no tools: the AI has to read each chart unaided. Scores run far lower than the with-tools version, so read the two as separate tests. Higher is better. | 46.4% | — |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Oct 7 2026 | Aug 13 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Haiku 5.5vsGPT-6.1 SolDeepSeek-V4-Pro-0813vsGPT-6.1 SolClaude Haiku 5.5vsGemini 4 ArgonDeepSeek-V4-Pro-0813vsGemini 4 ArgonClaude Haiku 5.5vsMuse Spark 1.3DeepSeek-V4-Pro-0813vsMuse Spark 1.3Claude Haiku 5.5vsGrok 4.7DeepSeek-V4-Pro-0813vsGrok 4.7Claude Haiku 5.5vsMistral Large 4DeepSeek-V4-Pro-0813vsMistral Large 4Claude Haiku 5.5vsKimi K3DeepSeek-V4-Pro-0813vsKimi K3Frequently asked questions
Claude Haiku 5.5 and DeepSeek-V4-Pro-0813 are evenly matched across the 2 benchmarks they both report (Humanity's Last Exam). Claude Haiku 5.5 is cheaper on both input and output: $0.10 vs $0.66 per million input tokens, and $0.50 vs $1.98 per million output tokens. Figures are base-tier rates. DeepSeek-V4-Pro-0813 shipped 55 days before Claude Haiku 5.5, so benchmark comparisons should account for the intervening progress.
Claude Haiku 5.5 is closed, while DeepSeek-V4-Pro-0813 is open weight.
On Humanity's Last Exam · no tools, Claude Haiku 5.5 leads at 45.9% vs DeepSeek-V4-Pro-0813 at 42.7%. On Humanity's Last Exam · with tools, DeepSeek-V4-Pro-0813 leads at 60% vs Claude Haiku 5.5 at 57.4%.