Salad Bench
Metriken
attack-enhanced-elo
attack-enhanced-safe%
base set-elo
base set-safe%
llm_model
model_url
organization
parameters
release_date
updated_time
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | attack-enhanced-elo | attack-enhanced-safe% | base set-elo | base set-safe% | llm_model | model_url | organization | parameters | release_date | updated_time |
|---|---|---|---|---|---|---|---|---|---|---|
| Modell 1 | 954 | 12.48 | 1016 | 90.45 | ChatGLM3-6B | https://github.com/THUDM/ChatGLM3 | THUDN | 6B | 2023.10.27 | 2024.8.11 |