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
•
32
Aletheia-Bench/DPO-Think-1.5B
Text Generation
•
2B
•
Updated
•
39
Aletheia-Bench/BatchOnline-GRPO-7B
Text Generation
•
8B
•
Updated
•
24
Aletheia-Bench/BatchOnline-GRPO-14B
Text Generation
•
15B
•
Updated
•
40
Aletheia-Bench/BatchOnline-GRPO-1.5B
Text Generation
•
2B
•
Updated
•
29
Aletheia-Bench/GRPO-Think-14B-8k
Text Generation
•
15B
•
Updated
•
30
Aletheia-Bench/GRPO-Think-7B-8k
Text Generation
•
8B
•
Updated
•
26
Aletheia-Bench/GRPO-Think-14B-4k
Text Generation
•
15B
•
Updated
•
25
Aletheia-Bench/RAFT-7B
8B
•
Updated
•
32
Aletheia-Bench/GRPO-Think-1.5B-8k
Text Generation
•
2B
•
Updated
•
23
datasets
6
Aletheia-Bench/Aletheia-Heldout
Viewer
•
Updated
•
33.3k
•
36
Aletheia-Bench/Aletheia-Strong
Viewer
•
Updated
•
57.3k
•
40
Aletheia-Bench/Aletheia-Train
Viewer
•
Updated
•
50k
•
17
Aletheia-Bench/Aletheia-Adv
Viewer
•
Updated
•
18k
•
51
Aletheia-Bench/Aletheia-DPO
Viewer
•
Updated
•
50k
•
13
Aletheia-Bench/Aletheia-Hard
Viewer
•
Updated
•
18k
•
36