Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Models · BLIP3-o (8B)6 results · 6 benchmarks
Model card

BLIP3-o (8B).

unknown
§ 02 · Benchmarks

Every benchmark BLIP3-o (8B) has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01VQA v2.0Multimodal · Visual Question Answeringaccuracy83.1%#4/16source ↗
02GenEvalMultimodal · Text-to-Image Generationgeneval-score0.8%#6/8source ↗
03TextVQAMultimodal · Visual Question Answeringaccuracy83.1%#11/23source ↗
04RealWorldQAMultimodal · Visual Question Answeringaccuracy69.0%#17/23source ↗
05MMMUMultimodal · Visual Question Answeringaccuracy50.6%#28/30source ↗
06MMMUMultimodal · Image-Text-to-Textaccuracy50.6%#31/36source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where BLIP3-o (8B) actually performs.

Multimodal
6
benchmarks
avg rank #16.2
§ 04 · Papers

1 paper with results for BLIP3-o (8B).

  1. 2025-05-14· 6 results

    BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
6
results
0 of 6 rows marked verified.