Compare models

Phi-4 vs Llama 3.3 70B 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.
Phi-4 vs Llama 3.3 70B Instruct, compared across 14 tracked fields. Each value shows the source that reported it and when.
FieldPhi-4Llama 3.3 70B Instruct
Downloads, 30 days
624,150Synced from sourceCurrentjust now
917,910 (highest of the compared values)Synced from sourceCurrentjust now
Likes
2,309Synced from sourceCurrentjust now
3,058 (highest of the compared values)Synced from sourceCurrentjust now
Context window
16,384Synced from sourceCurrentjust now
131,072 (highest of the compared values)Synced from sourceCurrentjust now
Input, $/M tokens
0.07 (lowest of the compared values)Synced from sourceCurrentjust now
0.1Synced from sourceCurrentjust now
Modality
textSeeded, unreviewedwritten 29d ago
textSeeded, unreviewedwritten 29d ago
Licence
mitSeeded, unreviewedwritten 29d ago
llama-3.3Seeded, unreviewedwritten 29d ago
Gated
noSynced from sourceCurrentjust now
manualSynced from sourceCurrentjust now
Last updated
2026-07-14Synced from sourceCurrentjust now
2024-12-21Synced from sourceCurrentjust now
Library
transformersSynced from sourceCurrentjust now
transformersSynced from sourceCurrentjust now
Task
text-generationSynced from sourceCurrentjust now
text-generationSynced from sourceCurrentjust now
Hugging Face
microsoft/phi-4Synced from sourceCurrentjust now
meta-llama/Llama-3.3-70B-InstructSynced from sourceCurrentjust now
OpenRouter id
microsoft/phi-4Synced from sourceCurrentjust now
meta-llama/llama-3.3-70b-instructSynced from sourceCurrentjust now
Output, $/M tokens
0.14Synced from sourceCurrentjust now
0.32Synced from sourceCurrentjust now
Vendor
MicrosoftSeeded, unreviewedwritten 29d ago
MetaSeeded, unreviewedwritten 29d ago

Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation just now. 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.