Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Pretraining on PleIAs SYNTH (val)
Loading...
0.7578
BPB (Validation)
ALPHALAB + Opus 4.6
0.738192
0.870546
1.0029
1.135254
Mar 31, 2026
BPB (Validation)
Updated 6d ago
Evaluation Results
Method
Method
Links
BPB (Validation)
ALPHALAB + Opus 4.6
Best config=10L×752d,...
2026.03
0.7578
ALPHALAB + Sonnet 4.6
Best config=11L×768d,...
2026.03
0.8686
ALPHALAB + GPT-5.2
Best config=8L×512d, G...
2026.03
0.9697
Greedy loop (GPT-5.2)
Best config=12L×768d,...
2026.03
1.02
Single-shot (GPT-5.2)
Best config=27.4M LLaM...
2026.03
1.248
Feedback
Search any
task
Search any
task