Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Symbolic planning on Countdown
Loading...
40.6
Exact-match Accuracy (Ngen=128)
DISPO
19.488
24.969
30.45
35.931
Feb 6, 2026
Exact-match Accuracy (Ngen=128)
Exact-match Accuracy (Ngen=256)
Exact-match Accuracy (Ngen=512)
Average Accuracy
Updated 5mo ago
Evaluation Results
Method
Method
Links
Exact-match Accuracy (Ngen=128)
Exact-match Accuracy (Ngen=256)
Exact-match Accuracy (Ngen=512)
Average Accuracy
DISPO
base_model=LLaDA-8B-In...
2026.02
40.6
37.1
39.8
39.2
DISPO
base_model=SFT w/ s1k,...
2026.02
37.5
32.8
40.2
36.8
diffu-GRPO
base_model=SFT w/ s1k,...
2026.02
34.8
32
42.2
36.3
diffu-GRPO
base_model=LLaDA-8B-In...
2026.02
33.2
31.3
37.1
33.9
LLaDA-8B-Instruct
base_model=LLaDA-8B-In...
2026.02
20.7
19.5
16
18.7
SFT w/ s1k
base_model=SFT w/ s1k
2026.02
20.3
14.5
23.8
19.5
Feedback
Search any
task
Search any
task