Compare models

Whisper large-v3 vs GPT-4o mini 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.
Whisper large-v3 vs GPT-4o mini vs GPT-4o, compared across 14 tracked fields. Each value shows the source that reported it and when.
FieldWhisper large-v3GPT-4o miniGPT-4o
Downloads, 30 days
4,471,077Synced from sourceCurrent5h ago
——
Likes
6,442Synced from sourceCurrent5h ago
——
Context window—
128,000Synced from sourceCurrent5h ago
128,000Synced from sourceCurrent5h ago
Input, $/M tokens—
0.15 (lowest of the compared values)Synced from sourceCurrent5h ago
2.5Synced from sourceCurrent5h ago
Modality
speechSeeded, unreviewedwritten 1mo ago
textSeeded, unreviewedwritten 1mo ago
textSeeded, unreviewedwritten 1mo ago
Licence
apache-2.0Seeded, unreviewedwritten 1mo ago
proprietarySeeded, unreviewedwritten 1mo ago
proprietarySeeded, unreviewedwritten 1mo ago
Gated
noSynced from sourceCurrent5h ago
——
Last updated
2024-08-12Synced from sourceCurrent5h ago
——
Library
transformersSynced from sourceCurrent5h ago
——
Task
automatic-speech-recognitionSynced from sourceCurrent5h ago
——
Hugging Face
openai/whisper-large-v3Synced from sourceCurrent5h ago
——
OpenRouter id—
openai/gpt-4o-miniSynced from sourceCurrent5h ago
openai/gpt-4oSynced from sourceCurrent5h ago
Output, $/M tokens—
0.6Synced from sourceCurrent5h ago
10Synced from sourceCurrent5h ago
Vendor
OpenAISeeded, unreviewedwritten 1mo ago
OpenAISeeded, unreviewedwritten 1mo ago
OpenAISeeded, unreviewedwritten 1mo ago

Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 5h 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.