koala-13B: benchmark results
Provider: Other.
Aggregate Rating 1258 ± 38, rank #9177 of 10916 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MT-Bench | 5.35 | MT-Bench average score (points) | 33.3 |
| MoralChoice | 92.4 | MoralChoice Acc (%) | 30 |
| Chatbot Arena (Text - Life, Physical & Social Science) | 1102 | Arena Score | 3.4 |
| Chatbot Arena (Text - English) | 1099 | Arena Score | 2.9 |
| Chatbot Arena (Text) | 1071 | Elo | 2.9 |
| Chatbot Arena (Text - Business, Management & Financial Ops) | 1048 | Arena Score | 2.5 |
| Chatbot Arena (Text - Creative Writing) | 1046 | Arena Score | 2.4 |
| Chatbot Arena (Text - Entertainment, Sports & Media) | 1031 | Arena Score | 2.4 |
| Chatbot Arena (Text - Hard Prompts) | 1035 | Arena Score | 2.4 |
| Chatbot Arena (Text - Instruction Following) | 1027 | Arena Score | 2.4 |
| Chatbot Arena (Text - Non-English) | 1007 | Arena Score | 2.4 |
| Chatbot Arena (Text - Software & IT Services) | 1073 | Arena Score | 2.4 |
Interactive version: theaggregate.ai/model?slug=koala-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.