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. | — | 284B |
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. | 200k | 1M |
| 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. | $5.00 | — |
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. | $25.00 | — |
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. | $0.50 | — |
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $5.00Amazon Bedrock | $0.0388Wafer |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $25.00Amazon Bedrock | $0.1599Relace |
| $2,250Anthropic list price | $15.96Relace · fp4 | |
| 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. | 90% | 39% |
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. | 80.9% | 79% |
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. | 30.8% | 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. | 37.64% | 61.4% |
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% |
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% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 87% | — |
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. | 66.3% | — |
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% |
threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. | 1138 | — |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Nov 24 2025 | Jul 31 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Opus 4.5vsGPT-6.1 TerraDeepSeek-V4-Flash-0731vsGPT-6.1 TerraClaude Opus 4.5vsGemini 4 CarbonDeepSeek-V4-Flash-0731vsGemini 4 CarbonClaude Opus 4.5vsMuse Spark OpenDeepSeek-V4-Flash-0731vsMuse Spark OpenClaude Opus 4.5vsGrok 4.7DeepSeek-V4-Flash-0731vsGrok 4.7Claude Opus 4.5vsMistral Large 4DeepSeek-V4-Flash-0731vsMistral Large 4Claude Opus 4.5vsKimi K3.1 ProDeepSeek-V4-Flash-0731vsKimi K3.1 ProFrequently asked questions
Claude Opus 4.5 and DeepSeek-V4-Flash-0731 are evenly matched across the 4 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, Humanity's Last Exam, ARC-AGI-2). Only Claude Opus 4.5 has a verified first-party price for an available API: $5.00 per million input tokens and $25.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek-V4-Flash-0731. Claude Opus 4.5 shipped 249 days before DeepSeek-V4-Flash-0731, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude Opus 4.5) vs 1M (DeepSeek-V4-Flash-0731). Claude Opus 4.5 is closed, while DeepSeek-V4-Flash-0731 is open weight.
On BullshitBench v2, Claude Opus 4.5 leads at 90% vs DeepSeek-V4-Flash-0731 at 39%. On SWE-Bench Verified, Claude Opus 4.5 leads at 80.9% vs DeepSeek-V4-Flash-0731 at 79%. On Humanity's Last Exam · with tools, DeepSeek-V4-Flash-0731 leads at 34.8% vs Claude Opus 4.5 at 30.8%. On ARC-AGI-2, DeepSeek-V4-Flash-0731 leads at 61.4% vs Claude Opus 4.5 at 37.64%.