mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_gpt5_gen4s_GEaprm_qwen3_ap_SE42_RE4-ap1_best_0020 Viewer • Updated about 7 hours ago • 1.59k
mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_gpt5_gen4s_GEaprm_qwen3_ap_SE42_RE4-ap1_0019 Viewer • Updated about 7 hours ago • 1.59k
mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_default_GEaprm_qwen3_ap_SE42_RE5-ap1_best_0040 Viewer • Updated about 9 hours ago • 12.7k
mzio/aprm_sft_thought_action_rollouts-ENhotpotqa_mc_default_GEaprm_qwen3_ap_SE42_RE5-ap1_0039 Viewer • Updated about 9 hours ago • 12.7k
mzio/rb_last-cql-mc_oai_gpt5_low-ec_hotpotqa_mc_gpt5-ds_train-spp1-gbs1-s42-r_0-v5649-tools Viewer • Updated about 10 hours ago • 5.65k
mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_2-ap_rl0020 Viewer • Updated 1 day ago • 9.91k • 21
mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_2-ap_rl0010 Viewer • Updated 1 day ago • 9.91k • 11
mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_2-ap_rl0000 Viewer • Updated 1 day ago • 9.91k • 30
mzio/aprm_sft_thought_action_rollouts-act_prm_browsecomp_100_hide_obs_aprm_qwen3_ap_42_1-ap_rl0000 Viewer • Updated 1 day ago • 9.91k • 33
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0080 Viewer • Updated 1 day ago • 1.02k • 12
mzio/aprm_sft-act_prm_browsecomp_100_aprm_qwen3_ap_42_debug-0020 Viewer • Updated 1 day ago • 2.12k • 19
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0070 Viewer • Updated 1 day ago • 4.06k • 11
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0070 Viewer • Updated 1 day ago • 4.06k • 11
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0060 Viewer • Updated 1 day ago • 1.02k • 12
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0060 Viewer • Updated 1 day ago • 1.02k • 11
mzio/aprm_sft-act_prm_browsecomp_100_aprm_qwen3_ap_42_debug-0010 Viewer • Updated 2 days ago • 7.2k • 19
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0050 Viewer • Updated 2 days ago • 4.06k • 17
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0050 Viewer • Updated 2 days ago • 4.06k • 13
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0040 Viewer • Updated 2 days ago • 1.02k • 11
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0040 Viewer • Updated 2 days ago • 1.02k • 13
mzio/aprm_sft-act_prm_hotpotqa_mc_250_hide_obs_aprm_qwen3_ap_42_0-0010 Viewer • Updated 2 days ago • 4.06k • 13
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0030 Viewer • Updated 2 days ago • 4.06k • 13
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0030 Viewer • Updated 2 days ago • 4.06k • 10
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0020 Viewer • Updated 2 days ago • 1.02k • 18
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_42_0-0020 Viewer • Updated 2 days ago • 1.02k • 19