Compare models
GPT-4o vs BGE-M3 vs Qwen2.5 72B 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 | GPT-4o | BGE-M3 | Qwen2.5 72B Instruct |
|---|---|---|---|
| Downloads, 30 days | — | 36,333,889 (highest of the compared values)Synced from sourceCurrent4h ago | 293,852Synced from sourceCurrent4h ago |
| Likes | — | 3,704 (highest of the compared values)Synced from sourceCurrent4h ago | 997Synced from sourceCurrent4h ago |
| Context window | 128,000 (highest of the compared values)Synced from sourceCurrent4h ago | — | 32,768Synced from sourceCurrent4h ago |
| Input, $/M tokens | 2.5Synced from sourceCurrent4h ago | — | 0.36 (lowest of the compared values)Synced from sourceCurrent4h ago |
| Modality | textSeeded, unreviewedwritten 1mo ago | embeddingSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago |
| Licence | proprietarySeeded, unreviewedwritten 1mo ago | mitSeeded, unreviewedwritten 1mo ago | qwenSeeded, unreviewedwritten 1mo ago |
| Gated | — | noSynced from sourceCurrent4h ago | noSynced from sourceCurrent4h ago |
| Last updated | — | 2024-07-03Synced from sourceCurrent4h ago | 2025-01-12Synced from sourceCurrent4h ago |
| Library | — | sentence-transformersSynced from sourceCurrent4h ago | transformersSynced from sourceCurrent4h ago |
| Task | — | sentence-similaritySynced from sourceCurrent4h ago | text-generationSynced from sourceCurrent4h ago |
| Hugging Face | — | BAAI/bge-m3Synced from sourceCurrent4h ago | Qwen/Qwen2.5-72B-InstructSynced from sourceCurrent4h ago |
| OpenRouter id | openai/gpt-4oSynced from sourceCurrent4h ago | — | qwen/qwen-2.5-72b-instructSynced from sourceCurrent4h ago |
| Output, $/M tokens | 10Synced from sourceCurrent4h ago | — | 0.4Synced from sourceCurrent4h ago |
| Vendor | OpenAISeeded, unreviewedwritten 1mo ago | BAAISeeded, unreviewedwritten 1mo ago | AlibabaSeeded, 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.