Discrimination on PsyCLIENT-CP +content
61.9Accuracy (A)Claude-Sonet-3.5
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Claude-Sonet-3.5LLM-as-a-judge=true2026.01 | 61.9 | 36.1 | |
| DeepSeek-R1LLM-as-a-judge=true2026.01 | 12.8 | 8.3 | |
| Qwen3-235B-A22BLLM-as-a-judge=true2026.01 | 5.6 | 10 | |
| DeepSeek-V3-0324LLM-as-a-judge=true2026.01 | 1.9 | 0.6 | |
| GPT-4oLLM-as-a-judge=true2026.01 | 0.8 | 5.8 | |
| Qwen2.5-72B-InstructLLM-as-a-judge=true2026.01 | 0.3 | 0.3 |