mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0040 Viewer • Updated Jan 18 • 1.02k • 11
mzio/aprm_sft-act_prm_hotpotqa_mc_250_hide_obs_aprm_qwen3_ap_42_0-0010 Viewer • Updated Jan 18 • 4.06k • 7
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0030 Viewer • Updated Jan 18 • 4.06k • 8
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0020 Viewer • Updated Jan 18 • 1.02k • 11
mzio/aprm_sft-act_prm_hotpotqa_mc_250_aprm_qwen3_ap_nobandit_42_0-0010 Viewer • Updated Jan 18 • 4.06k • 14
mzio/aprm_sft-act_prm_hotpotqa_mc_1k_aprm_qwen3_ap_nobandit_42_0-0010 Viewer • Updated Jan 17 • 16k • 10
mzio/rb_last-cql-mc_oai_gpt5_med-ec_browsecomp_plus_search_gpt5_multihop-ds_train-spp4-gbs1-s0-r_1 Viewer • Updated Dec 29, 2025 • 31.3k • 60
mzio/rb_last-cql-mc_oai_gpt5_med-ec_browsecomp_plus_search-ds_train-spp4-gbs1-s0-r_1 Viewer • Updated Dec 29, 2025 • 17.7k • 51
mzio/rb_last-cql-mc_oai_gpt5_med-ec_hotpotqa_mc_gpt5_4s-ds_train-spp1-gbs1-s42-r_0 Viewer • Updated Dec 26, 2025 • 4.44k • 12
mzio/rb_last-cql-mc_oai_gpt5_med-ec_hotpotqa_mc_gpt5-ds_train-spp1-gbs1-s42-r_0 Viewer • Updated Dec 26, 2025 • 5.66k • 13
mzio/rb_last-cql-mc_oai_gpt5_low-ec_hotpotqa_mc_gpt5_4s-ds_train-spp1-gbs1-s42-r_0 Viewer • Updated Dec 26, 2025 • 4.42k • 13
mzio/rb_last-cql-mc_oai_gpt5_low-ec_hotpotqa_mc_gpt5-ds_train-spp1-gbs1-s42-r_0 Viewer • Updated Dec 26, 2025 • 5.65k • 14
mzio/cql_gen-browsecomp_plus_qa_gen-oai_gpt5_low-multihop_2-v3187 Viewer • Updated Dec 15, 2025 • 3.19k • 27
mzio/g1_task_gen-olympus_task_gen-oai_gpt5_low-mt1-multi_r2-ns663 Viewer • Updated Nov 29, 2025 • 663 • 8
mzio/g1_task_gen-olympus_task_gen-oai_gpt5_low-mt1-multi_v2_r0-ns518 Viewer • Updated Nov 29, 2025 • 518 • 9
mzio/g1_task_gen-olympus_task_gen-oai_gpt5_med-mt1-multi_v2_r0-ns246 Viewer • Updated Nov 29, 2025 • 246 • 5
mzio/g1_task_gen-olympus_task_gen-oai_gpt5_low-mt1-multi_v2_r0 Viewer • Updated Nov 29, 2025 • 518 • 9
mzio/miq-slackchat_qa_open_gpt5mini-eval_gpt5-v0_1694-all-kmedoids100 Viewer • Updated Nov 23, 2025 • 100 • 9