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. | 200k | 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. | — | $0.66 |
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. | — | $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. | — | $0.022 |
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. | — | $0.0999Relace |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $1.98DeepSeek |
| — | $231DeepSeek list price | |
| Benchmarks | ||
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. | 22.2% | 80.6% |
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% |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 84.9% | — |
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% |
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. | — | 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. | — | 60% |
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% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 50.4% | — |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 88.2% | — |
Okapi Multilingual MMLUMultilingual knowledge — five-shot accuracy on the Okapi translations of MMLU used in the Claude 3 model card | 79.1% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 90.7% | — |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 95% | — |
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% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 59.4% | — |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Mar 4 2024 | Aug 13 2026 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude 3 OpusvsGPT-6.1 TerraDeepSeek-V4-Pro-0813vsGPT-6.1 TerraClaude 3 OpusvsGemini 4 HydrogenDeepSeek-V4-Pro-0813vsGemini 4 HydrogenClaude 3 OpusvsMuse EmberDeepSeek-V4-Pro-0813vsMuse EmberClaude 3 OpusvsGrok 4.7DeepSeek-V4-Pro-0813vsGrok 4.7Claude 3 OpusvsMistral Large 4DeepSeek-V4-Pro-0813vsMistral Large 4Claude 3 OpusvsKimi K3.1 ProDeepSeek-V4-Pro-0813vsKimi K3.1 ProFrequently asked questions
DeepSeek-V4-Pro-0813 leads Claude 3 Opus on 1 of the 1 benchmark they both report (SWE-Bench Verified). Only DeepSeek-V4-Pro-0813 has a verified first-party price for an available API: $0.66 per million input tokens and $1.98 per million output tokens. No currently available pay-as-you-go API rate is tracked for Claude 3 Opus. Claude 3 Opus shipped 892 days before DeepSeek-V4-Pro-0813, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude 3 Opus) vs 1M (DeepSeek-V4-Pro-0813). Claude 3 Opus is closed, while DeepSeek-V4-Pro-0813 is open weight.
On SWE-Bench Verified, DeepSeek-V4-Pro-0813 leads at 80.6% vs Claude 3 Opus at 22.2%.