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 · SigLIP 2 (g/16)5 results · 5 benchmarks
Model card

SigLIP 2 (g/16).

unknown
§ 02 · Benchmarks

Every benchmark SigLIP 2 (g/16) has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01ImageNet-V2Computer Vision · Image Classificationaccuracy79.8%#2/4source ↗
02Pascal VOC 2012Computer Vision · Object Detectionmiou78.1%#3/3source ↗
03ImageNet-1KComputer Vision · Image Classificationaccuracy85.0%#11/26source ↗
04ADE20KComputer Vision · Semantic Segmentationmiou45.4%#14/15source ↗
05COCOComputer Vision · Object Detectionmap45.2%#42/55source ↗
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 SigLIP 2 (g/16) actually performs.

Computer Vision
1
benchmark
avg rank #14.0
Computer Vision
4
benchmarks
avg rank #14.5
§ 04 · Papers

1 paper with results for SigLIP 2 (g/16).

  1. 2025-02-20· 5 results

    SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
5
results
0 of 5 rows marked verified.