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 Aug 25 • 68 Aletheia-Bench/GRPO-Think-7B-16k Text Generation • 8B • Updated Aug 25 • 67 Aletheia-Bench/GRPO-Think-14B-16k Text Generation • 15B • Updated Aug 25 • 62 Aletheia-Bench/GRPO-Think-1.5B-4k Text Generation • 2B • Updated Aug 25 • 62
Aletheia Datasets The datasets used in the Aletheia paper Aletheia-Bench/Aletheia-Train Viewer • Updated Aug 25 • 50k • 45 Aletheia-Bench/Aletheia-DPO Viewer • Updated Aug 25 • 50k • 30 Aletheia-Bench/Aletheia-Heldout Viewer • Updated Aug 25 • 33.3k • 31 Aletheia-Bench/Aletheia-Strong Viewer • Updated Aug 25 • 57.3k • 38
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 Aug 25 • 68 Aletheia-Bench/GRPO-Think-7B-16k Text Generation • 8B • Updated Aug 25 • 67 Aletheia-Bench/GRPO-Think-14B-16k Text Generation • 15B • Updated Aug 25 • 62 Aletheia-Bench/GRPO-Think-1.5B-4k Text Generation • 2B • Updated Aug 25 • 62
Aletheia Datasets The datasets used in the Aletheia paper Aletheia-Bench/Aletheia-Train Viewer • Updated Aug 25 • 50k • 45 Aletheia-Bench/Aletheia-DPO Viewer • Updated Aug 25 • 50k • 30 Aletheia-Bench/Aletheia-Heldout Viewer • Updated Aug 25 • 33.3k • 31 Aletheia-Bench/Aletheia-Strong Viewer • Updated Aug 25 • 57.3k • 38
