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 · ALIGN3 results · 3 benchmarks
Model card

ALIGN.

unknown
§ 02 · Benchmarks

Every benchmark ALIGN has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01COCO CaptionsMultimodal · Image Captioningr-159.9%#2/3source ↗
02ImageNet-1KComputer Vision · Image Classificationaccuracy88.6%#3/26source ↗
03ImageNet-V2Computer Vision · Image Classificationaccuracy70.1%#3/4source ↗
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 ALIGN actually performs.

Multimodal
1
benchmark
avg rank #2.0
Computer Vision
2
benchmarks
avg rank #3.0
§ 04 · Papers

1 paper with results for ALIGN.

  1. 2021-02-11· 3 results

    Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
3
results
0 of 3 rows marked verified.