Surrogate code verifiers across three model sizes trained using multiple different algorithms as described in the Aletheia paper
Aletheia
community
AI & ML interests
None defined yet.
Recent Activity
models 21
Aletheia-Bench/DPO-Think-14B
Text Generation • 15B • Updated • 4 • 1
Aletheia-Bench/DPO-Think-1.5B
Text Generation • 2B • Updated • 8
Aletheia-Bench/BatchOnline-GRPO-7B
Text Generation • 8B • Updated • 3 • 1
Aletheia-Bench/BatchOnline-GRPO-14B
Text Generation • 15B • Updated • 7 • 1
Aletheia-Bench/BatchOnline-GRPO-1.5B
Text Generation • 2B • Updated • 5
Aletheia-Bench/GRPO-Think-14B-8k
Text Generation • 15B • Updated • 3 • 1
Aletheia-Bench/GRPO-Think-7B-8k
Text Generation • 8B • Updated • 2
Aletheia-Bench/GRPO-Think-14B-4k
Text Generation • 15B • Updated
Aletheia-Bench/RAFT-7B
8B • Updated
Aletheia-Bench/GRPO-Think-1.5B-8k
Text Generation • 2B • Updated • 1
datasets 8
Aletheia-Bench/Aletheia-Mixed-DPO
Viewer • Updated • 50k • 7
Aletheia-Bench/Aletheia-Mixed
Viewer • Updated • 50k • 50
Aletheia-Bench/Aletheia-Heldout
Viewer • Updated • 33.3k • 35
Aletheia-Bench/Aletheia-Strong
Viewer • Updated • 57.3k • 32
Aletheia-Bench/Aletheia-Train
Viewer • Updated • 50k • 17
Aletheia-Bench/Aletheia-Adv
Viewer • Updated • 18k • 29
Aletheia-Bench/Aletheia-DPO
Viewer • Updated • 50k • 11
Aletheia-Bench/Aletheia-Hard
Viewer • Updated • 18k • 32