Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | — | 671B |
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 | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $10.00Verified organizations only | — |
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. | $50.00 | — |
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. | $1.00 | — |
| $4,500Anthropic list price | — | |
| These models have no shared benchmark scores. | ||
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 80.3% | — |
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. | 95.5% | — |
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. | — | 88.7% |
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. | 88% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 88% | — |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | 83.8% | — |
RiemannBenchAdvanced mathematics — mathematical problem-solving evaluation published by Surge | 55% | — |
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. | 59% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 30.6% |
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. | 64.5% | — |
BioMysteryBench · hardBiology — Real unsolved-style biology puzzles — the AI has to reason its way to an answer the way a research biologist would. The “hard” split contains the toughest cases. Higher is better. | 46.1% | — |
BioMysteryBench · human solvedBiology — Real biology puzzles that human experts have managed to crack — can the AI reach the same answers? Higher is better. | 83.9% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 96% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 85.7% |
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. | 85% | — |
Harvey's Legal Agent BenchmarkAgentic legal work — Harvey's test of whether an AI agent can complete real legal work — drafting and reviewing documents, working with spreadsheets and presentations, and navigating files the way a lawyer's assistant would. Higher is better. | 16.9% | — |
HealthBench Professional · rawHealth — physician-graded conversations, scored before adjustment for answer length | 70.3% | — |
HealthBench Professional · length-adjustedHealth — The same physician-graded health conversations as HealthBench Professional, scored with an adjustment for how long the answer is — so a model cannot gain by padding its reply. The adjustment moves scores by several points, so these numbers are not interchangeable with the unadjusted ones. Higher is better. | 66% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 88.9% | — |
CharXiv Reasoning · with toolsChart reasoning — The same chart-and-figure reasoning test, run with the AI allowed to use tools — writing code to inspect the image, for instance — rather than reading the chart unaided. Scores run higher than the unaided version, so read the two as separate tests. Higher is better. | 93.5% | — |
Chartography · with toolsChart tasks — A chart-centred test run with tools available to the AI, reported separately from the chart-reading benchmarks above it. Higher is better. | 85.2% | — |
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. | 36% | — |
OfficeQA Pro · extracted textDocument Q&A — answering the 133 Treasury document questions with extracted text and code execution available | 67.1% | — |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Jun 9 2026 | Dec 1 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Mythos 5vsGPT-6.2 AstraDeepSeek-V3.2-SpecialevsGPT-6.2 AstraClaude Mythos 5vsGemini 4 HydrogenDeepSeek-V3.2-SpecialevsGemini 4 HydrogenClaude Mythos 5vsMuse EmberDeepSeek-V3.2-SpecialevsMuse EmberClaude Mythos 5vsGrok 4.7DeepSeek-V3.2-SpecialevsGrok 4.7Claude Mythos 5vsMistral Large 4DeepSeek-V3.2-SpecialevsMistral Large 4Claude Mythos 5vsKimi K3.1 ProDeepSeek-V3.2-SpecialevsKimi K3.1 ProFrequently asked questions
Claude Mythos 5 and DeepSeek-V3.2-Speciale don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Claude Mythos 5 has a verified first-party price for an available API: $10.00 per million input tokens and $50.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek-V3.2-Speciale. Claude Mythos 5 requires organization verification. DeepSeek-V3.2-Speciale shipped 190 days before Claude Mythos 5, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Mythos 5) vs 128k (DeepSeek-V3.2-Speciale). Claude Mythos 5 is closed, while DeepSeek-V3.2-Speciale is open weight.
Direct benchmark comparisons are unavailable — Claude Mythos 5 and DeepSeek-V3.2-Speciale don't publish scores on any of the same benchmarks.