Compare models

Phi-4 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.
Phi-4 vs DeepSeek V3 vs BGE-M3, compared across 14 tracked fields. Each value shows the source that reported it and when.
FieldPhi-4DeepSeek V3BGE-M3
Downloads, 30 days
624,150Synced from sourceCurrent2h ago
1,134,368Synced from sourceCurrent2h ago
37,229,647 (highest of the compared values)Synced from sourceCurrent2h ago
Likes
2,309Synced from sourceCurrent2h ago
4,236 (highest of the compared values)Synced from sourceCurrent2h ago
3,615Synced from sourceCurrent2h ago
Context window
16,384Synced from sourceCurrent2h ago
163,840 (highest of the compared values)Synced from sourceCurrent2h ago
Input, $/M tokens
0.07 (lowest of the compared values)Synced from sourceCurrent2h ago
0.32Synced from sourceCurrent2h ago
Modality
textSeeded, unreviewedwritten 29d ago
textSeeded, unreviewedwritten 29d ago
embeddingSeeded, unreviewedwritten 29d ago
Licence
mitSeeded, unreviewedwritten 29d ago
deepseekSeeded, unreviewedwritten 29d ago
mitSeeded, unreviewedwritten 29d ago
Gated
noSynced from sourceCurrent2h ago
noSynced from sourceCurrent2h ago
noSynced from sourceCurrent2h ago
Last updated
2026-07-14Synced from sourceCurrent2h ago
2025-03-27Synced from sourceCurrent2h ago
2024-07-03Synced from sourceCurrent2h ago
Library
transformersSynced from sourceCurrent2h ago
transformersSynced from sourceCurrent2h ago
sentence-transformersSynced from sourceCurrent2h ago
Task
text-generationSynced from sourceCurrent2h ago
text-generationSynced from sourceCurrent2h ago
sentence-similaritySynced from sourceCurrent2h ago
Hugging Face
microsoft/phi-4Synced from sourceCurrent2h ago
deepseek-ai/DeepSeek-V3Synced from sourceCurrent2h ago
BAAI/bge-m3Synced from sourceCurrent2h ago
OpenRouter id
microsoft/phi-4Synced from sourceCurrent2h ago
deepseek/deepseek-chatSynced from sourceCurrent2h ago
Output, $/M tokens
0.14Synced from sourceCurrent2h ago
0.89Synced from sourceCurrent2h ago
Vendor
MicrosoftSeeded, unreviewedwritten 29d ago
DeepSeekSeeded, unreviewedwritten 29d ago
BAAISeeded, unreviewedwritten 29d ago

Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 2h 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.


Every figure on this site resolves to the source that reported it, the moment it was observed, and how it was measured. A value that fails validation is withheld rather than shown — withheld means we refused to publish it, not that it is zero.