aya-101: benchmark results
Provider: Cohere. Access: Open.
Unified ELO 1394 ± 37, rank #1226 of 1632 rated models, from 46 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open PL LLM - 8TAGS (multiple choice, 5-shot) | 76.28 | Accuracy (%) | 71.3 |
| Open PL LLM - PolEmo2-OUT (multiple choice, 5-shot) | 72.67 | Accuracy (%) | 69 |
| Open PL LLM - PPC (generative, 5-shot) | 73.2 | Accuracy (%) | 66.1 |
| Open PL LLM - EQ-Bench | 35.7 | EQ-Bench Score | 63.4 |
| Open PL LLM - 8TAGS (generative, 5-shot) | 73.4 | Accuracy (%) | 58.3 |
| Open PL LLM - PolQA Reranking (multiple choice, 5-shot) | 72.09 | Accuracy (%) | 57.9 |
| Open PL LLM - Belebele (generative, 5-shot) | 79.67 | Accuracy (%) | 54.4 |
| Open PL LLM - Belebele (multiple choice, 5-shot) | 79.67 | Accuracy (%) | 53.6 |
| Greek MMLU - Other | 57.05 | Accuracy (%) | 50.6 |
| Greek MMLU - Social Sciences | 62.16 | Accuracy (%) | 50.6 |
| Open PL LLM - KLEJ NER (multiple choice, 5-shot) | 46.06 | Accuracy (%) | 50.3 |
| Greek MMLU | 56.73 | Accuracy (%) | 49.4 |
Interactive version: theaggregate.ai/model?slug=aya-101 · How It Works · Data refreshed daily, snapshot 2026-10-08.