Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Suicide Detection on RSD Suicide D2 (test)
Loading...
0.526
Accuracy
Mental-R1
0.22024
0.29962
0.379
0.45838
Jun 11, 2026
Accuracy
Weighted F1-score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Weighted F1-score
Mental-R1
Architecture=CRPO-trained
2026.06
0.526
0.5014
GPT-5
Category=Industry-leve...
2026.06
0.4548
0.4308
DeepSeek-R1
Category=Industry-leve...
2026.06
0.45
0.4316
Mental-GLM
Category=Domain and pu...
2026.06
0.4243
0.3751
DeepSeek-V3
Category=Industry-leve...
2026.06
0.4234
0.4199
GPT-4o
Category=Industry-leve...
2026.06
0.4127
0.3569
Llama-3.1-SFT
Category=Domain and pu...
2026.06
0.2999
0.2652
Gemma-2-SFT
Category=Domain and pu...
2026.06
0.2946
0.2948
GPT-3.5
Category=Industry-leve...
2026.06
0.294
0.2987
Mentallama
Category=Domain and pu...
2026.06
0.232
0.2288
Feedback
Search any
task
Search any
task