Compare models
Mixtral 8x7B Instruct vs Mistral 7B Instruct v0.3 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 | Mixtral 8x7B Instruct | Mistral 7B Instruct v0.3 | DeepSeek R1 |
|---|---|---|---|
| Downloads, 30 days | 207,778Synced from sourceCurrent4h ago | 2,189,377 (highest of the compared values)Synced from sourceCurrent4h ago | 895,329Synced from sourceCurrent4h ago |
| Likes | 4,757Synced from sourceCurrent4h ago | 3,618Synced from sourceCurrent4h ago | 14,298 (highest of the compared values)Synced from sourceCurrent4h ago |
| Context window | — | — | 64,000Synced from sourceCurrent4h ago |
| Input, $/M tokens | — | — | 0.7Synced from sourceCurrent4h ago |
| Modality | textSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago | reasoningSeeded, unreviewedwritten 1mo ago |
| Licence | apache-2.0Seeded, unreviewedwritten 1mo ago | apache-2.0Seeded, unreviewedwritten 1mo ago | mitSeeded, unreviewedwritten 1mo ago |
| Gated | noSynced from sourceCurrent4h ago | noSynced from sourceCurrent4h ago | noSynced from sourceCurrent4h ago |
| Last updated | 2025-07-24Synced from sourceCurrent4h ago | 2025-12-03Synced from sourceCurrent4h ago | 2025-03-27Synced from sourceCurrent4h ago |
| Library | vllmSynced from sourceCurrent4h ago | vllmSynced from sourceCurrent4h ago | transformersSynced from sourceCurrent4h ago |
| Task | — | — | text-generationSynced from sourceCurrent4h ago |
| Hugging Face | mistralai/Mixtral-8x7B-Instruct-v0.1Synced from sourceCurrent4h ago | mistralai/Mistral-7B-Instruct-v0.3Synced from sourceCurrent4h ago | deepseek-ai/DeepSeek-R1Synced from sourceCurrent4h ago |
| OpenRouter id | — | — | deepseek/deepseek-r1Synced from sourceCurrent4h ago |
| Output, $/M tokens | — | — | 2.5Synced from sourceCurrent4h ago |
| Vendor | Mistral AISeeded, unreviewedwritten 1mo ago | Mistral AISeeded, unreviewedwritten 1mo ago | DeepSeekSeeded, unreviewedwritten 1mo ago |
Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 4h 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.