Decision-Making Bias Evaluation on ICE-GUARD
1.1Overall FRGLM-5
Evaluation Results
| Method | Links | |
|---|---|---|
| GLM-5Family=Zhipu AI2026.03 | 1.1 | |
| Claude Opus 4.6Family=Anthropic2026.03 | 1.3 | |
| GPT-OSS-120BFamily=OpenAI2026.03 | 1.3 | |
| GPT-5.2Family=OpenAI2026.03 | 3.7 | |
| Gemini 3 FlashFamily=Google2026.03 | 4 | |
| Gemini 2.5 ProFamily=Google2026.03 | 5.3 | |
| DeepSeek-V3.2Family=DeepSeek2026.03 | 5.3 | |
| Kimi-K2.5Family=Moonshot AI2026.03 | 5.5 | |
| Mistral-Small-24BFamily=Mistral AI2026.03 | 5.7 | |
| Claude Sonnet 4.5Family=Anthropic2026.03 | 6 | |
| Qwen3-32BFamily=Alibaba2026.03 | 7.7 |