Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Preference Evaluation on EQ-Bench Creative and LongBench Write (60 pairs)
Loading...
67.5
Winrate
POLARIS
50.548
54.949
59.35
63.751
Jun 2, 2026
Winrate
Win Rate (W)
Tie Rate (T)
Loss Rate (L)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Winrate
Win Rate (W)
Tie Rate (T)
Loss Rate (L)
POLARIS
Comparison Baseline=Qw...
2026.06
67.5
57.5
20
22.5
POLARIS
Comparison Baseline=Qw...
2026.06
51.2
35
32.5
32.5
Feedback
Search any
task
Search any
task