Compare models
BGE-M3 vs Phi-4 vs Qwen2.5 Coder 32B Instruct
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 | BGE-M3 | Phi-4 | Qwen2.5 Coder 32B Instruct |
|---|---|---|---|
| Downloads, 30 days | 36,333,889 (highest of the compared values)Synced from sourceCurrent3h ago | 591,256Synced from sourceCurrent3h ago | 1,046,114Synced from sourceCurrent3h ago |
| Likes | 3,704 (highest of the compared values)Synced from sourceCurrent3h ago | 2,312Synced from sourceCurrent3h ago | 2,155Synced from sourceCurrent3h ago |
| Context window | — | 16,384Synced from sourceCurrent3h ago | 32,768 (highest of the compared values)Synced from sourceCurrent3h ago |
| Input, $/M tokens | — | 0.07 (lowest of the compared values)Synced from sourceCurrent3h ago | 0.66Synced from sourceCurrent3h ago |
| Modality | embeddingSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago | codeSeeded, unreviewedwritten 1mo ago |
| Licence | mitSeeded, 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 | 2024-07-03Synced from sourceCurrent3h ago | 2026-07-14Synced from sourceCurrent3h ago | 2025-01-12Synced from sourceCurrent3h ago |
| Library | sentence-transformersSynced from sourceCurrent3h ago | transformersSynced from sourceCurrent3h ago | transformersSynced from sourceCurrent3h ago |
| Task | sentence-similaritySynced from sourceCurrent3h ago | text-generationSynced from sourceCurrent3h ago | text-generationSynced from sourceCurrent3h ago |
| Hugging Face | BAAI/bge-m3Synced from sourceCurrent3h ago | microsoft/phi-4Synced from sourceCurrent3h ago | Qwen/Qwen2.5-Coder-32B-InstructSynced from sourceCurrent3h ago |
| OpenRouter id | — | microsoft/phi-4Synced from sourceCurrent3h ago | qwen/qwen-2.5-coder-32b-instructSynced from sourceCurrent3h ago |
| Output, $/M tokens | — | 0.14Synced from sourceCurrent3h ago | 1Synced from sourceCurrent3h ago |
| Vendor | BAAISeeded, unreviewedwritten 1mo ago | MicrosoftSeeded, unreviewedwritten 1mo ago | AlibabaSeeded, 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.