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. | — | 14.3B |
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 | 32k |
| Benchmarks | ||
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. | 92.4% | 34.2% |
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. | 85.2% | 62.5% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 90% | — |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | 83.9 | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 70% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 60% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 89.9% | — |
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. | — | 61.5% |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Sep 12 2024 | Mar 28 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
o1-minivsClaude Fable 5.2Qwen1.5-MoEvsClaude Fable 5.2o1-minivsGemini 4 NeonQwen1.5-MoEvsGemini 4 Neono1-minivsMuse EmberQwen1.5-MoEvsMuse Embero1-minivsGrok 4.7Qwen1.5-MoEvsGrok 4.7o1-minivsDeepSeek-V4.1-Flash-1017Qwen1.5-MoEvsDeepSeek-V4.1-Flash-1017o1-minivsMistral Large 4Qwen1.5-MoEvsMistral Large 4Frequently asked questions
o1-mini leads Qwen1.5-MoE on 2 of the 2 benchmarks they both report (HumanEval, MMLU). Qwen1.5-MoE shipped 168 days before o1-mini, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (o1-mini) vs 32k (Qwen1.5-MoE). o1-mini is closed, while Qwen1.5-MoE is open weight.
On HumanEval, o1-mini leads at 92.4% vs Qwen1.5-MoE at 34.2%. On MMLU, o1-mini leads at 85.2% vs Qwen1.5-MoE at 62.5%.