Report Generation on Mental Health Social Media Twitter
3.9Trajectory CoverageGPT-traj
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GPT-trajEvaluator Model=GPT 5.22026.05 | 3.9 | 3.4 | 3.2 | 3.6 | 3.5 | |
| GPT-trajEvaluator Model=Claude Opus 4.62026.05 | 3.9 | 3.6 | 3.4 | 3.8 | 3.6 | |
| GPT-trajEvaluator Model=Gemini 3.1 pro2026.05 | 3.8 | 3.5 | 3.3 | 3.5 | 3.4 | |
| GPT-trajEvaluator Model=DeepSeek 3.22026.05 | 3.3 | 3.6 | 2.9 | 3.7 | 3.6 | |
| BaselineEvaluator Model=Gemini 3.1 pro2026.05 | 2.7 | 3 | 2.2 | 2.9 | 2.6 | |
| BaselineEvaluator Model=GPT 5.22026.05 | 2.5 | 2.8 | 1.9 | 2.6 | 2.6 | |
| BaselineEvaluator Model=Claude Opus 4.62026.05 | 2.4 | 2.7 | 2.1 | 2.4 | 2.4 | |
| BaselineEvaluator Model=DeepSeek 3.22026.05 | 1.7 | 2 | 1.3 | 1.3 | 1.8 |