Discrimination on PsyCLIENT-CP +behavior
26.1Accuracy (A)DeepSeek-R1
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DeepSeek-R1LLM-as-a-judge=true2026.01 | 26.1 | 9.2 | |
| Claude-Sonet-3.5LLM-as-a-judge=true2026.01 | 14.4 | 7.5 | |
| Qwen3-235B-A22BLLM-as-a-judge=true2026.01 | 14.2 | 17.2 | |
| DeepSeek-V3-0324LLM-as-a-judge=true2026.01 | 1.4 | 0.3 | |
| GPT-4oLLM-as-a-judge=true2026.01 | 0.6 | 0.6 | |
| Qwen2.5-72B-InstructLLM-as-a-judge=true2026.01 | 0 | 0 |