Skip to content

Benchmark

Indigenous Americas Cloze Accuracy Improvement (Shipibo-Konibo)

Higher scores are better.

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

10
Mean
11
Median
1.4
Std dev
8
10th percentile
11
90th percentile
8
Min
811
The band covers the middle 80% of scores. The line marks the median.

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

ModelScore
DeepSeek V3table: 3, language: Shipibo-Konibo· Indigenous Americas linguistic competence data docs11
Gemini 2.0 Flashtable: 3, language: Shipibo-Konibo· Indigenous Americas linguistic competence data docs11
GPT 4.1table: 3, language: Shipibo-Konibo· Indigenous Americas linguistic competence data docs8

Data credits: Vasselli, Martínez Peguero, Hudi, Sakajo and Watanabe. Measuring Linguistic Competence of LLMs on Indigenous Languages of the Americas. EACL 2026, ©2026 ACL, CC BY 4.0. Numeric/protocol extract from Tables 1–4; random reference rows omitted. (licence)