Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
CoT Length Prediction on GPQA Diamond
Loading...
27.32
Relative MAE
Fuel Gauge
26.026
34.7605
43.495
52.2295
Mar 11, 2026
Relative MAE
Updated 1mo ago
Evaluation Results
Method
Method
Links
Relative MAE
Fuel Gauge
Backbone Model=Qwen3-8B
2026.03
27.32
Fuel Gauge
Backbone Model=Qwen3-4B
2026.03
31.85
Direct
Backbone Model=Qwen3-4B
2026.03
49.32
Mean
Backbone Model=Qwen3-8B
2026.03
50.03
Median
Backbone Model=Qwen3-8B
2026.03
52.12
Mean
Backbone Model=Qwen3-4B
2026.03
57.21
Direct
Backbone Model=Qwen3-8B
2026.03
57.95
Median
Backbone Model=Qwen3-4B
2026.03
59.67
Feedback
Search any
task
Search any
task