WildChat

anchor

Findings

• IC-206GPT-4o-0513 achieves the highest wb-reward mix score (35.7) on WildBench, with a clear three-tier structure among 40 evaluated LLMs [source]
• IC-252GPT models produce harmful gender stereotypes at higher rates when user names imply a demographic group, with GPT-3.5 Turbo showing the highest rates and open-ended generation tasks most affected [source]
• IC-253Post-training reinforcement learning significantly reduces harmful gender stereotypes in GPT models, with the best-fit slope of 0.21 indicating post-RL models have far lower bias than pre-RL versions [source]
• IC-254GPT-4o Mini responses to female-sounding names systematically use simpler, more light-hearted, and less technical language compared to male-sounding names across multiple task domains [source]
• IC-255GPT-4o, Llama 3.1, and Claude models show varying correlation with human ratings when used as stereotype evaluators, with GPT-4o achieving the strongest gender correlation (ρ=0.86) but weaker racial correlations [source]
• IC-761GPT-3.5-turbo and GPT-4 are susceptible to specific circulating jailbreaking prompts, with 'jailmommy' achieving a 71.16% success rate in producing toxic outputs [source]