Benchmark
Indigenous Americas Cloze Accuracy Improvement (Quechua)
Higher scores are better.
- Models measured
- 3
- Scores recorded
- 3
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 38.3
- Mean
- 36
- Median
- 4.8
- Std dev
- 34
- 10th percentile
- 45
- 90th percentile
- 34
- Min
Results
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model | Score |
|---|---|
| DeepSeek V3table: 3, language: Quechua· Indigenous Americas linguistic competence data docs | 36 |
| Gemini 2.0 Flashtable: 3, language: Quechua· Indigenous Americas linguistic competence data docs | 45 |
| GPT 4.1table: 3, language: Quechua· Indigenous Americas linguistic competence data docs | 34 |
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)