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. | — | 1.6T |
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 | 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 | $0.90Relace |
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 | $1.50Relace |
| $2,250Anthropic list price | $255Relace · 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. | 87% | 14% |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.7% | 83.4% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.3% | 90.1% |
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% |
ProgramBenchProgram reconstruction — The AI receives a working program and its documentation, then builds a replacement from scratch without the original source code, internet access or decompilation. The score is the percentage of 200 programs that pass every behavioral test. We record each model's best published mini-SWE-agent result, including higher reasoning efforts where available. Partial test-pass rates and almost-solved programs do not count toward this score. Equal scores share a rank here; the official board also uses partial progress to break ties. Higher is better. | 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. | 80.8% | — |
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 58% | — |
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% |
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. | 53% | — |
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. | 68.75% | — |
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. | 72.7% | — |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Feb 5 2026 | Apr 24 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude Opus 4.6vsGPT-6.1 SolDeepSeek-V4-ProvsGPT-6.1 SolClaude Opus 4.6vsGemini 4 ArgonDeepSeek-V4-ProvsGemini 4 ArgonClaude Opus 4.6vsMuse Spark OpenDeepSeek-V4-ProvsMuse Spark OpenClaude Opus 4.6vsGrok 4.7DeepSeek-V4-ProvsGrok 4.7Claude Opus 4.6vsMistral Large 4DeepSeek-V4-ProvsMistral Large 4Claude Opus 4.6vsKimi K3DeepSeek-V4-ProvsKimi K3Frequently asked questions
Claude Opus 4.6 leads DeepSeek-V4-Pro on 3 of the 3 benchmarks they both report (BullshitBench v2, BrowseComp, GPQA Diamond). Only Claude Opus 4.6 has a verified first-party API price: $5.00 per million input tokens and $25.00 per million output tokens. No pay-as-you-go API rate is tracked for DeepSeek-V4-Pro. Claude Opus 4.6 shipped 78 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Opus 4.6) vs 1M (DeepSeek-V4-Pro). Claude Opus 4.6 is closed, while DeepSeek-V4-Pro is open weight.
On BullshitBench v2, Claude Opus 4.6 leads at 87% vs DeepSeek-V4-Pro at 14%. On BrowseComp, Claude Opus 4.6 leads at 83.7% vs DeepSeek-V4-Pro at 83.4%. On GPQA Diamond, Claude Opus 4.6 leads at 91.3% vs DeepSeek-V4-Pro at 90.1%.