Trained Verifier Models Surrogate code verifiers across three model sizes trained using multiple different algorithms as described in the Aletheia paper Aletheia-Bench/GRPO-Think-1.5B-16k Text Generation • 2B • Updated 8 days ago • 285 Aletheia-Bench/GRPO-Think-7B-16k Text Generation • 8B • Updated 8 days ago • 308 Aletheia-Bench/GRPO-Think-14B-16k Text Generation • 15B • Updated 8 days ago • 291 Aletheia-Bench/GRPO-Think-1.5B-4k Text Generation • 2B • Updated 8 days ago • 281
Aletheia Datasets The datasets used in the Aletheia paper Aletheia-Bench/Aletheia-Train Viewer • Updated 8 days ago • 50k • 63 Aletheia-Bench/Aletheia-DPO Viewer • Updated 8 days ago • 50k • 60 Aletheia-Bench/Aletheia-Heldout Viewer • Updated 8 days ago • 33.3k • 70 Aletheia-Bench/Aletheia-Strong Viewer • Updated 8 days ago • 57.3k • 80
Trained Verifier Models Surrogate code verifiers across three model sizes trained using multiple different algorithms as described in the Aletheia paper Aletheia-Bench/GRPO-Think-1.5B-16k Text Generation • 2B • Updated 8 days ago • 285 Aletheia-Bench/GRPO-Think-7B-16k Text Generation • 8B • Updated 8 days ago • 308 Aletheia-Bench/GRPO-Think-14B-16k Text Generation • 15B • Updated 8 days ago • 291 Aletheia-Bench/GRPO-Think-1.5B-4k Text Generation • 2B • Updated 8 days ago • 281
Aletheia Datasets The datasets used in the Aletheia paper Aletheia-Bench/Aletheia-Train Viewer • Updated 8 days ago • 50k • 63 Aletheia-Bench/Aletheia-DPO Viewer • Updated 8 days ago • 50k • 60 Aletheia-Bench/Aletheia-Heldout Viewer • Updated 8 days ago • 33.3k • 70 Aletheia-Bench/Aletheia-Strong Viewer • Updated 8 days ago • 57.3k • 80
