Long Context Evaluation on Humanity's Last Exam AA-LCR
54.3AccuracyGLM-4.6
Evaluation Results
| Method | Links | |
|---|---|---|
| GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=English, Sub-Dataset=AA-LCR2026.01 | 54.3 | |
| DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=English, Sub-Dataset=AA-LCR2026.01 | 53.3 | |
| A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=English, Sub-Dataset=AA-LCR2026.01 | 36 | |
| GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=English, Sub-Dataset=Humanity's Last Exam2026.01 | 13.3 | |
| DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=English, Sub-Dataset=Humanity's Last Exam2026.01 | 13 | |
| A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=English, Sub-Dataset=Humanity's Last Exam2026.01 | 8.6 |