Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Numerical Reasoning on Countdown-4
Loading...
98.9
CD4
Self-Aware Markov Models
38.788
54.394
70
85.606
Mar 17, 2026
CD4
Updated 1mo ago
Evaluation Results
Method
Method
Links
CD4
Self-Aware Markov Models
Params=34M, Training s...
2026.03
98.9
Self-Aware Markov Models
Params=34M, Model arch...
2026.03
95.9
Self-Aware Markov Models (Small variant)
Params=11M, Model arch...
2026.03
92.1
MGDM
Params=85M, Model arch...
2026.03
91.5
DFM
Params=34M, Model arch...
2026.03
87.5
RDM
Params=85M, Model arch...
2026.03
87
D3PM
Params=85M, Model arch...
2026.03
83.1
VDM
Params=85M, Model arch...
2026.03
73.4
Stream-of-Search
Params=250M, Model arc...
2026.03
54.2
LLaMA
Params=13B, Model arch...
2026.03
51.1
GPT-2 Scratch
Params=85M, Model arch...
2026.03
45.8
GPT-2 Scratch
Params=303M, Model arc...
2026.03
41.3
LLaMA
Params=7B, Model archi...
2026.03
41.1
Feedback
Search any
task
Search any
task