c4ai-aya-expanse-8B: benchmark results
Provider: Cohere. Released 2024-10-24. Access: Open.
Aggregate Rating 1475 ± 51, rank #2740 of 10916 rated models, from 31 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Enkrypt AI - Jailbreak Risk | 3.82 | Risk Score | 84.7 |
| Enkrypt AI - Toxicity Risk | 1.05 | Risk Score | 83 |
| Enkrypt AI - Safety Risk | 20.51 | Risk Score | 82.3 |
| Enkrypt AI - Insecure Code Risk | 19.11 | Risk Score | 64 |
| Enkrypt AI - Risk Score | 28.56 | Risk Score | 62.5 |
| Vectara Hallucination Leaderboard | 90.5 | Factual Consistency Rate (%) | 51.4 |
| Enkrypt AI - Bias Risk | 85.01 | Risk Score | 42.2 |
| Chatbot Arena (Text - Non-English) | 1212 | Arena Score | 22 |
| Chatbot Arena (Text - Life, Physical & Social Science) | 1250 | Arena Score | 21 |
| Chatbot Arena (Text - Business, Management & Financial Ops) | 1228 | Arena Score | 20.9 |
| Chatbot Arena (Text - Writing, Literature & Language) | 1213 | Arena Score | 20.6 |
| Chatbot Arena (Text - Multi-Turn) | 1200 | Arena Score | 20 |
Interactive version: theaggregate.ai/model?slug=c4ai-aya-expanse-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.