Rumor Victim Susceptibility on CoPHEME
52.6ASR (Charlie Hebdo)Claude-4.5-Haiku
Evaluation Results
| Method | Links | |||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude-4.5-HaikuModel Family=Proprietary2026.01 | 52.6 | 0.74 | 20.6 | 34.5 | 0.7 | 10.3 | 32 | 0.71 | 8 | 50.9 | 0.74 | 14.6 | 63.6 | 0.77 | 34.5 | 16.7 | 0.61 | 16.7 | 42.4 | |
| Qwen2.5-3B-InstModel Family=Open-Weights2026.01 | 54.7 | 0.88 | 51.2 | 59.4 | 0.88 | 53.1 | 52.3 | 0.88 | 49.2 | 64.4 | 0.88 | 60 | 45.3 | 0.9 | 43.4 | 31 | 0.78 | 20.7 | 55.4 | |
| Qwen2.5-7B-InstModel Family=Open-Weights2026.01 | 67.8 | 0.86 | 62.1 | 82.4 | 0.84 | 68.5 | 62 | 0.85 | 56.5 | 64 | 0.86 | 54.3 | 65.5 | 0.86 | 61.8 | 36.7 | 0.8 | 26.7 | 67.1 | |
| Open-Weights Avg.Model Family=Open-Weights2026.01 | 69.3 | 0.85 | 58.9 | 80.4 | 0.83 | 65.2 | 64.6 | 0.83 | 54 | 76 | 0.85 | 64.6 | 61.4 | 0.86 | 53.3 | 54.5 | 0.76 | 33.6 | 70.6 | |
| DS-R1-Distill-Qwen-1.5BModel Family=Open-Weights2026.01 | 71 | 0.76 | 50.8 | 81 | 0.76 | 55.6 | 61.1 | 0.7 | 37.6 | 72.5 | 0.74 | 47.5 | 79.1 | 0.73 | 51.2 | 75 | 0.62 | 33.3 | 71.6 | |
| Qwen2.5-14B-InstModel Family=Open-Weights2026.01 | 71.4 | 0.85 | 59.5 | 81.3 | 0.82 | 62.6 | 60.2 | 0.83 | 46.9 | 85.9 | 0.85 | 69.3 | 53.9 | 0.89 | 50 | 69 | 0.75 | 27.6 | 71.9 | |
| DS-R1-Distill-Qwen-7BModel Family=Open-Weights2026.01 | 74.9 | 0.88 | 66.3 | 92.1 | 0.85 | 75.2 | 76 | 0.87 | 69.5 | 81.2 | 0.89 | 74.5 | 66 | 0.92 | 60.4 | 66.7 | 0.86 | 60 | 79.2 | |
| Claude-3.5-HaikuModel Family=Proprietary2026.01 | 76.9 | 0.81 | 47.9 | 76.9 | 0.79 | 45 | 77.1 | 0.79 | 46.9 | 80.5 | 0.77 | 38.4 | 61.8 | 0.82 | 38.2 | 74.1 | 0.71 | 18.5 | 76.7 | |
| DS-R1-Distill-Qwen-14BModel Family=Open-Weights2026.01 | 77 | 0.86 | 64.9 | 83.6 | 0.85 | 71.5 | 74.9 | 0.84 | 64.3 | 88.5 | 0.88 | 84.2 | 54.5 | 0.91 | 52.7 | 36.7 | 0.74 | 20 | 76.8 | |
| GPT-4.1Model Family=Proprietary2026.01 | 77.1 | 0.88 | 73.7 | 64.8 | 0.88 | 60.6 | 60 | 0.87 | 57.5 | 77 | 0.89 | 74.5 | 54.5 | 0.94 | 54.5 | 16.7 | 0.9 | 16.7 | 65.9 | |
| Proprietary Avg.Model Family=Proprietary2026.01 | 78 | 0.82 | 60.1 | 78.8 | 0.8 | 55.7 | 68.3 | 0.8 | 46.2 | 81.4 | 0.82 | 61.2 | 64.7 | 0.85 | 53.3 | 51.8 | 0.76 | 23.6 | 74.4 | |
| GPT-4oModel Family=Proprietary2026.01 | 79.4 | 0.85 | 66.9 | 88.5 | 0.83 | 69.1 | 67 | 0.83 | 53 | 85.5 | 0.85 | 74.5 | 56.4 | 0.89 | 52.7 | 63.3 | 0.75 | 26.7 | 77.4 | |
| GPT-4.1-miniModel Family=Proprietary2026.01 | 79.9 | 0.85 | 68.4 | 80.6 | 0.82 | 50.9 | 68 | 0.81 | 42.5 | 77.6 | 0.87 | 67.9 | 63.6 | 0.91 | 63.6 | 20 | 0.81 | 16.7 | 72.7 | |
| GPT-4o-miniModel Family=Proprietary2026.01 | 81.7 | 0.83 | 67.4 | 92.1 | 0.82 | 70.3 | 79.5 | 0.81 | 59 | 86.7 | 0.85 | 78.2 | 74.5 | 0.85 | 60 | 66.7 | 0.82 | 53.3 | 83.1 | |
| GPT-4.1-nanoModel Family=Proprietary2026.01 | 81.7 | 0.81 | 66.9 | 94.5 | 0.8 | 67.1 | 79.1 | 0.79 | 53.1 | 94.5 | 0.81 | 74.8 | 74.5 | 0.83 | 61.8 | 70 | 0.75 | 13.3 | 85.5 | |
| Claude-3-HaikuModel Family=Proprietary2026.01 | 94.8 | 0.8 | 69 | 98.8 | 0.79 | 72 | 83.5 | 0.76 | 50 | 98.8 | 0.79 | 66.9 | 68.5 | 0.82 | 61.1 | 86.7 | 0.71 | 26.7 | 91.5 |