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 · Ovis2.5-9B9 results · 8 benchmarks
Model card

Ovis2.5-9B.

unknown1 current SOTA
§ 02 · Benchmarks

Every benchmark Ovis2.5-9B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01OCRBench v2Computer Vision · General OCR Capabilitiesenglish-score63.4%#1/2source ↗
02TextVQAMultimodal · Visual Question Answeringaccuracy91.2%#1/23source ↗
03OCRBench v2Computer Vision · General OCR Capabilitieschinese-score58.0%#2/2source ↗
04DocVQAComputer Vision · Document Understandinganls96.3%#6/21source ↗
05MMStarMultimodal · Image-Text-to-Textaccuracy72.4%#12/21source ↗
06MVBenchMultimodal · Video Understandingaccuracy69.7%#13/20source ↗
07Video-MMEMultimodal · Video Understandingaccuracy72.8%#13/24source ↗
08MMMUMultimodal · Image-Text-to-Textaccuracy71.2%#14/36source ↗
09MMMU-ProMultimodal · Visual Question Answeringaccuracy54.4%#22/31source ↗
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 Ovis2.5-9B actually performs.

Computer Vision
2
benchmarks
avg rank #3.0 · 1 SOTA
Multimodal
6
benchmarks
avg rank #12.5
§ 04 · Papers

1 paper with results for Ovis2.5-9B.

  1. 2025-08-15· 9 results

    Ovis2.5 Technical Report

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
9
results
0 of 9 rows marked verified.