o1-minivsQwen2.5
o1-mini | Qwen2.5 | |
|---|---|---|
| Specifications | ||
Parameters | — | 72B |
Context window | 128k | 128k |
| Benchmarks | ||
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 60% | — |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Sep 12 2024 | Sep 19 2024 |
| Access | Proprietary | Open Weight |
Which is better: o1-mini or Qwen2.5?
o1-mini and Qwen2.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. o1-mini shipped 7 days before Qwen2.5, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (o1-mini) vs 128k (Qwen2.5). o1-mini is proprietary, while Qwen2.5 is open weight.
Direct benchmark comparisons are unavailable — o1-mini and Qwen2.5 don't publish scores on any of the same benchmarks.
Frequently asked questions
o1-mini was released by OpenAI on Sep 12 2024.
Qwen2.5 was released by Qwen on Sep 19 2024.
o1-mini has a 128k context window; Qwen2.5 has 128k.
o1-mini is a proprietary model released by OpenAI. Qwen2.5 is an open weight model released by Qwen.