AGIdex
SUB-CAPABILITY · COMMUNICATION

Multilingual

105%
vs. HUMAN BASELINE = 100
SolvedConf · High

Scoring rubric

0–20
Early research
20–40
Narrow benchmark competence
40–60
Strong benchmark · reliability gaps
60–80
Human-competitive in common scenarios
80–100
Comparable to typical skilled adult
100+
Reliably exceeds typical human baseline

Score vs. baseline

Trend · Last 12 months
12mo ago   %
6mo ago   %
Today   %
Δ 12mo   +0

What this measures

Human baseline

A typical adult is monolingual or bilingual with limited cross-language transfer.

Human frontier

High-quality translation and generation across 200+ languages including low-resource ones.

Current state

What works

Cross-lingual transfer across major language families at scale.

Key gaps

Long-tail languages with under 1M speakers; dialectal variation within languages.

Evidence

1 source
TechnologyQualitySourceScore vs. baselineScore
Gemini 3.1 Provendor reporteddeepmind.google/models/model-cards/gemini-3-1-pro
110%
Source: github.com/facebookresearch/flores · Last reviewed May 2026