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. | 671B | 21B |
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. | 128k | 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. | — | $0.018AkashML |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $0.09AkashML |
| — | $8.10Darkbloom · fp8 | |
| 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. | 49.2% | 60.7% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 79.8% | 92.1% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 71.5% | 71.5% |
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. | 90.8% | 85.3% |
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. | 65.9% | — |
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. | — | 10.9% |
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. | — | 17.3% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 97.3% | — |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | 92.2 | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 91.7% |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 30.1% | — |
MMMLUKnowledge — average accuracy on multilingual translations of MMLU | — | 75.7% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 84% | — |
HealthBench · full setHealthcare — physician rubric score on the full set of the original HealthBench evaluation | — | 42.5% |
HealthBench · hardHealthcare — physician rubric score on the hard subset of the original HealthBench evaluation | — | 10.8% |
HealthBench · consensusHealthcare — physician rubric score on the consensus subset of the original HealthBench evaluation | — | 82.6% |
| Overview | ||
| Company | DeepSeek | OpenAI |
| Release date | Jan 20 2025 | Aug 5 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1vsClaude Fable 5.2gpt-oss-20bvsClaude Fable 5.2DeepSeek R1vsGemini 4 Hydrogengpt-oss-20bvsGemini 4 HydrogenDeepSeek R1vsMuse Embergpt-oss-20bvsMuse EmberDeepSeek R1vsGrok 4.7gpt-oss-20bvsGrok 4.7DeepSeek R1vsMistral Large 4gpt-oss-20bvsMistral Large 4DeepSeek R1vsKimi K3.1 Progpt-oss-20bvsKimi K3.1 ProFrequently asked questions
gpt-oss-20b leads DeepSeek R1 on 2 of the 4 benchmarks they both report (SWE-Bench Verified, AIME 2024, GPQA Diamond, MMLU). DeepSeek R1 shipped 197 days before gpt-oss-20b, so benchmark comparisons should account for the intervening progress.
DeepSeek R1 has 671B parameters, while gpt-oss-20b has 21B. Context windows are 128k (DeepSeek R1) vs 128k (gpt-oss-20b).
On SWE-Bench Verified, gpt-oss-20b leads at 60.7% vs DeepSeek R1 at 49.2%. On AIME 2024, gpt-oss-20b leads at 92.1% vs DeepSeek R1 at 79.8%. On GPQA Diamond, both models score 71.5%. On MMLU, DeepSeek R1 leads at 90.8% vs gpt-oss-20b at 85.3%.