Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
BDI/E State Understanding on BDI/E State Inference Comprehension Mode (test)
Loading...
71.1
E-A Metric
CogWM
30.332
40.916
51.5
62.084
Jun 28, 2026
E-A Metric
B-Sim Score
D-Sim Score
I-Sim Score
L-E Error
L-B Error
L-D Error
L-I Error
Updated 26d ago
Evaluation Results
Method
Method
Links
E-A Metric
B-Sim Score
D-Sim Score
I-Sim Score
L-E Error
L-B Error
L-D Error
L-I Error
CogWM
Model Size=14B
2026.06
71.1
73.9
67.1
44
3.71
2.92
3.27
4.29
GPT-5.5
2026.06
42.3
48.9
45.7
47.1
2.39
2.05
2.19
1.92
Qwen3
Model Size=14B
2026.06
32.4
39.8
36.1
41.9
2.33
1.63
1.79
1.55
DSv4-Pro
2026.06
31.9
46.8
43
42.5
1.95
2.02
2.2
1.89
Feedback
Search any
task
Search any
task