Benchmark Almanac

Gemini Embedding 2

Gemini Embedding 2 places in the top three on 2 benchmarks.

Google DeepMind Released March 10th, 2026 The lab's model card Compare with others
7
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
Google DeepMind Mar 2026

Gemini Embedding 2

Closed weights

No Epoch Capabilities Index score yet

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Vision, audio and robotics

BenchmarkScoreRankSource
MSEB 23.5 #2 of 9 Official leaderboard
VATEX 68.8 #2 of 5 Lab model card
Docci 93.4 #1 of 1 Lab model card
MSR-VTT retrieval 68.0 #1 of 1 Lab model card
TextCaps 89.6 #1 of 1 Lab model card
ViDoRe v2 64.9 #1 of 1 Lab model card
YouCook2 retrieval 52.5 #1 of 1 Lab model card

Its lab's number next to a leaderboard

Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.

Benchmark Lab says Board says Gap
MSEB 73.9 Gemini Embedding 2, speech to text MSEB mRR@10 23.5 Leaderboard +50.4

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it.