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 | ||
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. | — | $0.30Relace |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $1.9105StreamLake |
| Benchmarks | ||
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 88% | 83.4% |
CheatBenchCheating rate — Measures how often AI agents try to cheat on difficult assignments, such as reading hidden answers, copying work or manipulating grading. The overall score gives equal weight to ten categories; the sycophancy category measures how far an agent shifts its beliefs toward a user's stated views. Scores describe each model in its tested agent setup, and task success is measured separately. Lower is better. | — | 75.1% |
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. | — | 14% |
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. | — | 93.5% |
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% | — |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | 88% | — |
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% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 90.1% |
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% | — |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Jun 9 2026 | Apr 24 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Mythos 5vsGPT-6.1 SolDeepSeek-V4-ProvsGPT-6.1 SolClaude Mythos 5vsGemini 4 ArgonDeepSeek-V4-ProvsGemini 4 ArgonClaude Mythos 5vsMuse Spark 1.3DeepSeek-V4-ProvsMuse Spark 1.3Claude Mythos 5vsGrok 4.7DeepSeek-V4-ProvsGrok 4.7Claude Mythos 5vsMistral Large 4DeepSeek-V4-ProvsMistral Large 4Claude Mythos 5vsKimi K3DeepSeek-V4-ProvsKimi K3Frequently asked questions
Claude Mythos 5 leads DeepSeek-V4-Pro on 1 of the 1 benchmark they both report (BrowseComp). DeepSeek-V4-Pro shipped 46 days before Claude Mythos 5, so benchmark comparisons should account for the intervening progress.
Claude Mythos 5 is closed, while DeepSeek-V4-Pro is open weight.
On BrowseComp, Claude Mythos 5 leads at 88% vs DeepSeek-V4-Pro at 83.4%.