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
• 14 • 1
Aletheia-Bench/DPO-Think-1.5B
Text Generation • 2B • Updated
• 10
Aletheia-Bench/BatchOnline-GRPO-7B
Text Generation • 8B • Updated
• 8 • 1
Aletheia-Bench/BatchOnline-GRPO-14B
Text Generation • 15B • Updated
• 8 • 1
Aletheia-Bench/BatchOnline-GRPO-1.5B
Text Generation • 2B • Updated
• 7
Aletheia-Bench/GRPO-Think-14B-8k
Text Generation • 15B • Updated
• 2 • 1
Aletheia-Bench/GRPO-Think-7B-8k
Text Generation • 8B • Updated
• 3
Aletheia-Bench/GRPO-Think-14B-4k
Text Generation • 15B • Updated
• 3
Aletheia-Bench/RAFT-7B
8B • Updated
• 9
Aletheia-Bench/GRPO-Think-1.5B-8k
Text Generation • 2B • Updated
• 4
datasets 6
Aletheia-Bench/Aletheia-Heldout
Viewer
• Updated
• 33.3k • 31
Aletheia-Bench/Aletheia-Strong
Viewer
• Updated
• 57.3k • 33
Aletheia-Bench/Aletheia-Train
Viewer
• Updated
• 50k • 9
Aletheia-Bench/Aletheia-Adv
Viewer
• Updated
• 18k • 26
Aletheia-Bench/Aletheia-DPO
Viewer
• Updated
• 50k • 25
Aletheia-Bench/Aletheia-Hard
Viewer
• Updated
• 18k • 31