Microsoft
The Phi-3-Vision-128K-Instruct is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision.
Running this yourself: consumer gpu should be enough.
The Phi-3-Vision-128K-Instruct is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision.
Live access is not confirmed for this model. No current purchase price is advertised.
No current subscription pricing is tracked for this model.
Confirm this specific model, usage limits, and billing terms with the provider. A subscription does not automatically include API credits.
No login needed to compare. Prices are in USD; provider charges are separate from AI Market Cap plans. Context length, caching, tools, taxes, and regional terms can change the final cost. Open weights do not mean free hosting.
36.2
Quality Score
881
Arena ELO
4B
Parameters
131K
Context
This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.
18 of 22 public signals
Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.
This model has normalized benchmark rows, so scores here are directly comparable across benchmark sources.
Sign in to join the discussion
42.6K
Downloads
979
Likes
May 2024
Released
5/5 signals
4/4 signals
3/5 signals
3/4 signals
3/4 signals
Parameters
4B
Training compute
Not reported
Dataset scale
Not reported
Base model
Not reported
Gaps we are still tracking
Metadata sources
These are recent benchmark or leaderboard claims from official provider sources. They are useful for freshness and context, but they are not treated the same as normalized independent benchmark rows.
Another No. 1 spot! MAI-Transcribe-2 takes first place for transcription accuracy in David AI's new benchmark. MAI-Transcribe-2 has the lowest error rate in 18 of 21 languages.
Another No. 1 spot! MAI-Transcribe-2 takes first place for transcription accuracy in David AI's new benchmark. MAI-Transcribe-2 has the lowest error rate in 18 of 21 languages.
View sourcemicrosoft/Phi-3-vision-128k-instruct · Hugging Face
Microsoft published benchmark or leaderboard evidence for Phi-3-vision-128k-instruct.
View sourcemicrosoft/Phi-3-vision-128k-instruct · Hugging Face
Microsoft published benchmark or leaderboard evidence for Phi-3-vision-128k-instruct.
View source881
ELO Score
862 - 900
95% Confidence
+/-19 points
1.4K
Battles
Oct 12, 2026
Last Updated