DCAgent3/medagentbench_rl__56GPU_base_zclip__exp_rpt_pymethods2test_large__GLM_4_7_swesm235edc8a Viewer • Updated May 27 • 966 • 10
DCAgent3/gaia_127_a3_rl_DCAgent_inferredbugs_sandboxes_verifier_55_8B_20260526_230125 Viewer • Updated May 27 • 584 • 28
DCAgent3/financeagent_terminal_a3_rl_DCAgent_llm_verifier_freelancer_70_8B_20260526_230418 Viewer • Updated May 26 • 156 • 16
DCAgent3/aider_polyglot_Qwen3_32B_31600_sera_46_47000_converted_20260526_075757-traces Viewer • Updated May 26 • 674 • 10
DCAgent3/medagentbench_GLM_4_7_swesmith_sandboxes_with_tests_oracle_verified_120s_maxepse931edb8 Viewer • Updated May 26 • 1.43k • 10
DCAgent3/gaia_127_maxgn09_hint__exp_rpt_pymethods2test_large__GLM_4_7_swesmith_san__Open83d703d6 Viewer • Updated May 26 • 806 • 23
DCAgent3/gaia_127_sft__pymethods2test_selfsuccess_best1_jsonfmt__laion_GLM_4_7_swesmith_5f0f8493 Viewer • Updated May 26 • 769 • 29
DCAgent3/dev_set_v2_rl__24GPU_base_lr5e_6__exp_rpt_pymethods2test_large__GLM_4_7_swesmit39f22783 Viewer • Updated May 26 • 440 • 8
DCAgent3/financeagent_terminal_GLM_4_7_swesmith_sandboxes_with_tests_oracle_verified_120ba231273 Viewer • Updated May 26 • 156 • 12
DCAgent3/swebench_verified_random_100_folders_a3_rl_DCAgent2_nl2bash_tasks_cleaned_oracl108cf924 Viewer • Updated May 26 • 505 • 10
DCAgent3/gaia_127_rl_swesmith_fixthink_pymethods2test_45_20260526_201917 Viewer • Updated May 26 • 860 • 37
DCAgent3/gaia_127_rl__24GPU_base__exp_rpt_pymethods2test_large__GLM_4_7_swesmith_san__401a7ffbf1 Viewer • Updated May 26 • 752 • 27
DCAgent3/gaia_127_rl__24GPU_base_lr5e_6__exp_rpt_pymethods2test_large__GLM_4_7_swesmith_93d5635e Viewer • Updated May 26 • 656 • 22
DCAgent3/bfcl_parity_a3_rl_DCAgent2_nl2bash_tasks_cleaned_oracle_40_8B_20260526_214917 Viewer • Updated May 26 • 372 • 14
DCAgent3/bfcl_parity_a3_rl_DCAgent_inferredbugs_sandboxes_verifier_55_8B_20260526_214919 Viewer • Updated May 26 • 369 • 7
DCAgent3/bfcl_parity_a3_rl_DCAgent_exp_rpt_curriculum_easy_21_8B_20260526_214915 Viewer • Updated May 26 • 371 • 8
DCAgent3/gaia_127_rl__56GPU_base_zclip__exp_rpt_pymethods2test_large__GLM_4_7_swesmith_sf2698d8e Viewer • Updated May 26 • 803 • 31
DCAgent3/swebench_verified_random_100_folders_a3_rl_DCAgent_exp_rpt_curriculum_easy_21_880803ee7 Viewer • Updated May 26 • 644 • 12
DCAgent3/gaia_127_rl__56GPU_base_staleclip__exp_rpt_pymethods2test_large__GLM_4_7_swesmi3c76f697 Viewer • Updated May 26 • 757 • 27
DCAgent3/dev_set_v2_a3_rl_DCAgent2_nl2bash_tasks_cleaned_oracle_40_8B_20260526_182634 Viewer • Updated May 26 • 342 • 9
DCAgent3/bfcl_parity_rl_think_npfg_code_contests_900s_45_20260526_201344 Viewer • Updated May 26 • 369 • 8
DCAgent3/bfcl_parity_rl_swesmith_fixthink_pymethods2test_45_20260526_201342 Viewer • Updated May 26 • 369 • 7
DCAgent3/dev_set_v2_a3_rl_DCAgent_exp_rpt_curriculum_easy_21_8B_20260526_182749 Viewer • Updated May 26 • 444 • 10
DCAgent3/bfcl_parity_sft__pymethods2test_selfsuccess_best1_jsonfmt__laion_GLM_4_7_swesmi28d0a993 Viewer • Updated May 26 • 404 • 7
DCAgent3/terminal_bench_2_a3_rl_DCAgent_exp_rpt_curriculum_easy_21_8B_20260526_182749 Viewer • Updated May 26 • 540 • 10
DCAgent3/bfcl_parity_rl__24GPU_base__exp_rpt_pymethods2test_large__GLM_4_7_swesmith_san_81076218 Viewer • Updated May 26 • 369 • 8
DCAgent3/bfcl_parity_maxgn09_hint__exp_rpt_pymethods2test_large__GLM_4_7_swesmith_san__Ofbba3cb9 Viewer • Updated May 26 • 369 • 8
DCAgent3/bfcl_parity_rl__24GPU_base_lr5e_6__exp_rpt_pymethods2test_large__GLM_4_7_swesmib8da1191 Viewer • Updated May 26 • 369 • 9
DCAgent3/bfcl_parity_rl__56GPU_base_staleclip__exp_rpt_pymethods2test_large__GLM_4_7_swefcca64c4 Viewer • Updated May 26 • 369 • 8
DCAgent3/bfcl_parity_GLM_4_7_swesmith_sandboxes_with_tests_oracle_verified_120s_maxeps_1015c97b3 Viewer • Updated May 26 • 369 • 8