Compare models

Llama 3.3 70B Instruct vs Claude Sonnet 5

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.
Llama 3.3 70B Instruct vs Claude Sonnet 5, compared across 14 tracked fields. Each value shows the source that reported it and when.
FieldLlama 3.3 70B InstructClaude Sonnet 5
Downloads, 30 days
904,760Synced from sourceCurrent2h ago
—
Likes
3,066Synced from sourceCurrent2h ago
—
Context window
131,072Synced from sourceCurrent2h ago
1,000,000 (highest of the compared values)Synced from sourceCurrent2h ago
Input, $/M tokens
0.1 (lowest of the compared values)Synced from sourceCurrent2h ago
2Synced from sourceCurrent2h ago
Modality
textSeeded, unreviewedwritten 1mo ago
textSeeded, unreviewedwritten 1mo ago
Licence
llama-3.3Seeded, unreviewedwritten 1mo ago
proprietarySeeded, unreviewedwritten 1mo ago
Gated
manualSynced from sourceCurrent2h ago
—
Last updated
2024-12-21Synced from sourceCurrent2h ago
—
Library
transformersSynced from sourceCurrent2h ago
—
Task
text-generationSynced from sourceCurrent2h ago
—
Hugging Face
meta-llama/Llama-3.3-70B-InstructSynced from sourceCurrent2h ago
—
OpenRouter id
meta-llama/llama-3.3-70b-instructSynced from sourceCurrent2h ago
anthropic/claude-sonnet-5Synced from sourceCurrent2h ago
Output, $/M tokens
0.32Synced from sourceCurrent2h ago
10Synced from sourceCurrent2h ago
Vendor
MetaSeeded, unreviewedwritten 1mo ago
AnthropicSeeded, unreviewedwritten 1mo 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.