Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language-based Games on StrBuild (test)
Loading...
1,620
Adjacency
Discussion
-23.2
403.4
830
1,256.6
Jan 29, 2026
Adjacency
IoU
Updated 5mo ago
Evaluation Results
Method
Method
Links
Adjacency
IoU
Discussion
Response time (seconds...
2026.01
1,620
6.5
Parallel
Response time (seconds...
2026.01
1,570
5.9
MAGRPO
Response time (seconds...
2026.01
1,330
50.6
Pipeline
Response time (seconds...
2026.01
1,290
18.7
CoLLM-DC
Response time (seconds...
2026.01
760
44.6
CoLLM-CC
Response time (seconds...
2026.01
730
68.5
Raw Model
Response time (seconds...
2026.01
90
36.6
GRPO
Response time (seconds...
2026.01
40
46.1
AC
Response time (seconds...
2026.01
40
49.8
Feedback
Search any
task
Search any
task