Compare models
GPT-4o mini vs DeepSeek V3 vs BGE-M3
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 | GPT-4o mini | DeepSeek V3 | BGE-M3 |
|---|---|---|---|
| Downloads, 30 days | — | 1,163,331Synced from sourceCurrent4h ago | 36,333,889 (highest of the compared values)Synced from sourceCurrent4h ago |
| Likes | — | 4,308 (highest of the compared values)Synced from sourceCurrent4h ago | 3,704Synced from sourceCurrent4h ago |
| Context window | 128,000Synced from sourceCurrent4h ago | 163,840 (highest of the compared values)Synced from sourceCurrent4h ago | — |
| Input, $/M tokens | 0.15 (lowest of the compared values)Synced from sourceCurrent4h ago | 0.26Synced from sourceCurrent4h ago | — |
| Modality | textSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago | embeddingSeeded, unreviewedwritten 1mo ago |
| Licence | proprietarySeeded, unreviewedwritten 1mo ago | deepseekSeeded, unreviewedwritten 1mo ago | mitSeeded, unreviewedwritten 1mo ago |
| Gated | — | noSynced from sourceCurrent4h ago | noSynced from sourceCurrent4h ago |
| Last updated | — | 2025-03-27Synced from sourceCurrent4h ago | 2024-07-03Synced from sourceCurrent4h ago |
| Library | — | transformersSynced from sourceCurrent4h ago | sentence-transformersSynced from sourceCurrent4h ago |
| Task | — | text-generationSynced from sourceCurrent4h ago | sentence-similaritySynced from sourceCurrent4h ago |
| Hugging Face | — | deepseek-ai/DeepSeek-V3Synced from sourceCurrent4h ago | BAAI/bge-m3Synced from sourceCurrent4h ago |
| OpenRouter id | openai/gpt-4o-miniSynced from sourceCurrent4h ago | deepseek/deepseek-chatSynced from sourceCurrent4h ago | — |
| Output, $/M tokens | 0.6Synced from sourceCurrent4h ago | 1.03Synced from sourceCurrent4h ago | — |
| Vendor | OpenAISeeded, unreviewedwritten 1mo ago | DeepSeekSeeded, unreviewedwritten 1mo ago | BAAISeeded, 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.