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. | 8B | 2B/7B |
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. | — | 8k |
| These models have no shared benchmark scores. | ||
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. | 60.5% | — |
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. | — | 32.3% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 24.3% |
ARC-ChallengeReasoning — multiple-choice science questions from the AI2 Reasoning Challenge; unrelated to ARC-AGI | — | 53.2% |
HellaSwagReasoning — commonsense completion of short scenarios | — | 81.2% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 86% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 76.3% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 61.1% | — |
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. | — | 64.3% |
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. | — | 46.4% |
| Overview | ||
| Company | DeepSeek | |
| Release date | May 29 2025 | Feb 21 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek R1-0528 Qwen3 8BvsClaude Fable 5.2Gemma 1vsClaude Fable 5.2DeepSeek R1-0528 Qwen3 8BvsGPT-6.2 AstraGemma 1vsGPT-6.2 AstraDeepSeek R1-0528 Qwen3 8BvsMuse EmberGemma 1vsMuse EmberDeepSeek R1-0528 Qwen3 8BvsGrok 4.7Gemma 1vsGrok 4.7DeepSeek R1-0528 Qwen3 8BvsMistral Large 4Gemma 1vsMistral Large 4DeepSeek R1-0528 Qwen3 8BvsKimi K3.1 ProGemma 1vsKimi K3.1 ProFrequently asked questions
DeepSeek R1-0528 Qwen3 8B and Gemma 1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Gemma 1 shipped 463 days before DeepSeek R1-0528 Qwen3 8B, so benchmark comparisons should account for the intervening progress.
DeepSeek R1-0528 Qwen3 8B has 8B parameters, while Gemma 1 has 2B/7B.
Direct benchmark comparisons are unavailable — DeepSeek R1-0528 Qwen3 8B and Gemma 1 don't publish scores on any of the same benchmarks.