Compare models
Qwen2.5 Coder 32B Instruct vs DeepSeek R1 vs Mistral 7B Instruct v0.3
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 Coder 32B Instruct | DeepSeek R1 | Mistral 7B Instruct v0.3 |
|---|---|---|---|
| Downloads, 30 days | 1,046,114Synced from sourceCurrent3h ago | 895,329Synced from sourceCurrent3h ago | 2,189,377 (highest of the compared values)Synced from sourceCurrent3h ago |
| Likes | 2,155Synced from sourceCurrent3h ago | 14,298 (highest of the compared values)Synced from sourceCurrent3h ago | 3,618Synced from sourceCurrent3h ago |
| Context window | 32,768Synced from sourceCurrent3h ago | 64,000 (highest of the compared values)Synced from sourceCurrent3h ago | — |
| Input, $/M tokens | 0.66 (lowest of the compared values)Synced from sourceCurrent3h ago | 0.7Synced from sourceCurrent3h ago | — |
| Modality | codeSeeded, unreviewedwritten 1mo ago | reasoningSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago |
| Licence | apache-2.0Seeded, unreviewedwritten 1mo ago | mitSeeded, unreviewedwritten 1mo ago | apache-2.0Seeded, unreviewedwritten 1mo ago |
| Gated | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago | noSynced from sourceCurrent3h ago |
| Last updated | 2025-01-12Synced from sourceCurrent3h ago | 2025-03-27Synced from sourceCurrent3h ago | 2025-12-03Synced from sourceCurrent3h ago |
| Library | transformersSynced from sourceCurrent3h ago | transformersSynced from sourceCurrent3h ago | vllmSynced from sourceCurrent3h ago |
| Task | text-generationSynced from sourceCurrent3h ago | text-generationSynced from sourceCurrent3h ago | — |
| Hugging Face | Qwen/Qwen2.5-Coder-32B-InstructSynced from sourceCurrent3h ago | deepseek-ai/DeepSeek-R1Synced from sourceCurrent3h ago | mistralai/Mistral-7B-Instruct-v0.3Synced from sourceCurrent3h ago |
| OpenRouter id | qwen/qwen-2.5-coder-32b-instructSynced from sourceCurrent3h ago | deepseek/deepseek-r1Synced from sourceCurrent3h ago | — |
| Output, $/M tokens | 1Synced from sourceCurrent3h ago | 2.5Synced from sourceCurrent3h ago | — |
| Vendor | AlibabaSeeded, unreviewedwritten 1mo ago | DeepSeekSeeded, unreviewedwritten 1mo ago | Mistral AISeeded, unreviewedwritten 1mo ago |
Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 3h 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.