Compare models
Qwen2.5 72B Instruct vs DeepSeek V3 vs DeepSeek R1
Every figure below carries the source that reported it and the moment it was observed. Values that failed validation are withheld rather than shown, and a dash means no source we track carries that field for that model.
| Field | Qwen2.5 72B Instruct | DeepSeek V3 | DeepSeek R1 |
|---|---|---|---|
| Downloads, 30 days | 326,043Synced from sourceCurrent1h ago | 1,134,368 (highest of the compared values)Synced from sourceCurrent1h ago | 815,126Synced from sourceCurrent1h ago |
| Likes | 994Synced from sourceCurrent1h ago | 4,236Synced from sourceCurrent1h ago | 14,285 (highest of the compared values)Synced from sourceCurrent1h ago |
| Context window | 32,768Synced from sourceCurrent1h ago | 163,840 (highest of the compared values)Synced from sourceCurrent1h ago | 64,000Synced from sourceCurrent1h ago |
| Input, $/M tokens | 0.36Synced from sourceCurrent1h ago | 0.32 (lowest of the compared values)Synced from sourceCurrent1h ago | 0.7Synced from sourceCurrent1h ago |
| Modality | textSeeded, unreviewedwritten 29d ago | textSeeded, unreviewedwritten 29d ago | reasoningSeeded, unreviewedwritten 29d ago |
| Licence | qwenSeeded, unreviewedwritten 29d ago | deepseekSeeded, unreviewedwritten 29d ago | mitSeeded, unreviewedwritten 29d ago |
| Gated | noSynced from sourceCurrent1h ago | noSynced from sourceCurrent1h ago | noSynced from sourceCurrent1h ago |
| Last updated | 2025-01-12Synced from sourceCurrent1h ago | 2025-03-27Synced from sourceCurrent1h ago | 2025-03-27Synced from sourceCurrent1h ago |
| Library | transformersSynced from sourceCurrent1h ago | transformersSynced from sourceCurrent1h ago | transformersSynced from sourceCurrent1h ago |
| Task | text-generationSynced from sourceCurrent1h ago | text-generationSynced from sourceCurrent1h ago | text-generationSynced from sourceCurrent1h ago |
| Hugging Face | Qwen/Qwen2.5-72B-InstructSynced from sourceCurrent1h ago | deepseek-ai/DeepSeek-V3Synced from sourceCurrent1h ago | deepseek-ai/DeepSeek-R1Synced from sourceCurrent1h ago |
| OpenRouter id | qwen/qwen-2.5-72b-instructSynced from sourceCurrent1h ago | deepseek/deepseek-chatSynced from sourceCurrent1h ago | deepseek/deepseek-r1Synced from sourceCurrent1h ago |
| Output, $/M tokens | 0.4Synced from sourceCurrent1h ago | 0.89Synced from sourceCurrent1h ago | 2.5Synced from sourceCurrent1h ago |
| Vendor | AlibabaSeeded, unreviewedwritten 29d ago | DeepSeekSeeded, unreviewedwritten 29d ago | DeepSeekSeeded, unreviewedwritten 29d ago |
Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 1h ago. Where a row is marked, ▲ is the highest of the values shown and ▼ the lowest — arithmetic on the figures above, not a ranking or a recommendation. Rows where neither extreme is meaningful are left unmarked rather than given a direction they do not have.
Change the comparison
Remove one, or open the directory to pick a different set. Up to 3 at a time.