Compare models
Qwen2.5 72B Instruct vs Gemma 2 9B Instruct vs GPT-4o
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 72B Instruct | Gemma 2 9B Instruct | GPT-4o |
|---|---|---|---|
| Downloads, 30 days | 293,852Synced from sourceCurrent4h ago | 1,143,286 (highest of the compared values)Synced from sourceCurrent4h ago | — |
| Likes | 997Synced from sourceCurrent4h ago | 1,023 (highest of the compared values)Synced from sourceCurrent4h ago | — |
| Context window | 32,768Synced from sourceCurrent4h ago | — | 128,000 (highest of the compared values)Synced from sourceCurrent4h ago |
| Input, $/M tokens | 0.36 (lowest of the compared values)Synced from sourceCurrent4h ago | — | 2.5Synced from sourceCurrent4h ago |
| Modality | textSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago | textSeeded, unreviewedwritten 1mo ago |
| Licence | qwenSeeded, unreviewedwritten 1mo ago | gemmaSeeded, unreviewedwritten 1mo ago | proprietarySeeded, unreviewedwritten 1mo ago |
| Gated | noSynced from sourceCurrent4h ago | manualSynced from sourceCurrent4h ago | — |
| Last updated | 2025-01-12Synced from sourceCurrent4h ago | 2024-08-27Synced from sourceCurrent4h ago | — |
| Library | transformersSynced from sourceCurrent4h ago | transformersSynced from sourceCurrent4h ago | — |
| Task | text-generationSynced from sourceCurrent4h ago | text-generationSynced from sourceCurrent4h ago | — |
| Hugging Face | Qwen/Qwen2.5-72B-InstructSynced from sourceCurrent4h ago | google/gemma-2-9b-itSynced from sourceCurrent4h ago | — |
| OpenRouter id | qwen/qwen-2.5-72b-instructSynced from sourceCurrent4h ago | — | openai/gpt-4oSynced from sourceCurrent4h ago |
| Output, $/M tokens | 0.4Synced from sourceCurrent4h ago | — | 10Synced from sourceCurrent4h ago |
| Vendor | AlibabaSeeded, unreviewedwritten 1mo ago | GoogleSeeded, unreviewedwritten 1mo ago | OpenAISeeded, 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.