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 | 117B |
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 | ||
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. | $0.90Relace | $0.03AkashML |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.50Relace | $0.15Near AI |
| $255Relace · fp4 | $13.50Venice · int4 | |
| 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. | 14% | 12% |
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% | 80.1% |
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% | — |
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. | — | 62.4% |
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% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | — |
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. | — | 14.9% |
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. | — | 19% |
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. | — | 90% |
| Overview | ||
| Company | DeepSeek | OpenAI |
| Release date | Apr 24 2026 | Aug 5 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-ProvsClaude Haiku 5.5gpt-oss-120bvsClaude Haiku 5.5DeepSeek-V4-ProvsGemini 4 Argongpt-oss-120bvsGemini 4 ArgonDeepSeek-V4-ProvsMuse Spark Opengpt-oss-120bvsMuse Spark OpenDeepSeek-V4-ProvsGrok 4.7gpt-oss-120bvsGrok 4.7DeepSeek-V4-ProvsMistral Large 4gpt-oss-120bvsMistral Large 4DeepSeek-V4-ProvsKimi K3gpt-oss-120bvsKimi K3Frequently asked questions
DeepSeek-V4-Pro leads gpt-oss-120b on 2 of the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). gpt-oss-120b shipped 262 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Pro has 1.6T parameters, while gpt-oss-120b has 117B. Context windows are 1M (DeepSeek-V4-Pro) vs 128k (gpt-oss-120b).
On BullshitBench v2, DeepSeek-V4-Pro leads at 14% vs gpt-oss-120b at 12%. On GPQA Diamond, DeepSeek-V4-Pro leads at 90.1% vs gpt-oss-120b at 80.1%.