Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Social Reasoning on EQBench 3
Loading...
84.5
Rubric Score
CTC-GRPO 32B
73.06
76.03
79
81.97
Jun 14, 2026
Rubric Score
Rubric Public Rank
Elo Score
Elo Public Rank
Updated 1mo ago
Evaluation Results
Method
Method
Links
Rubric Score
Rubric Public Rank
Elo Score
Elo Public Rank
CTC-GRPO 32B
Model size=32B, Traini...
2026.06
84.5
6
1,150
20
CTC-GRPO 8B
Model size=8B, Trainin...
2026.06
80.1
22
901
31
Qwen3-32B base
Model size=32B, Traini...
2026.06
74.3
33
948
31
Qwen3-8B base
Model size=8B, Trainin...
2026.06
73.5
32
745
38
Feedback
Search any
task
Search any
task