DCAgent3/financeagent_terminal_a3_rl_DCAgent_exp_rpt_e2egit_v2_10_8B_20260527_202838 Viewer • Updated May 27 • 154 • 13
DCAgent3/medagentbench_a3_rl_DCAgent_exp_rpt_e2egit_v2_10_8B_20260527_202829 Viewer • Updated May 27 • 1.36k • 11 • 1
DCAgent3/aider_polyglot_a3_rl_DCAgent2_nl2bash_tasks_cleaned_oracle_40_8B_20260526_230123 Viewer • Updated May 27 • 790 • 9
DCAgent3/bfcl_parity_a3_rl_DCAgent_exp_rpt_e2egit_v2_10_8B_20260527_202810 Viewer • Updated May 27 • 371 • 11 • 1
DCAgent3/dev_set_v2_rl__24GPU_base_excl_timeouts__exp_rpt_pymethods2test_large__GLM_4_7_c2148a8d Viewer • Updated May 27 • 296 • 12 • 1
DCAgent3/medagentbench_rl__24GPU_base_excl_timeouts__exp_rpt_pymethods2test_large__GLM_499e63853 Viewer • Updated May 27 • 1.09k • 12
DCAgent3/gaia_127_a3_rl_DCAgent2_nl2bash_tasks_cleaned_oracle_40_8B_20260526_230123-traces Viewer • Updated May 27 • 440 • 25
DCAgent3/gaia_127_a3_rl_DCAgent_exp_rpt_curriculum_easy_21_8B_20260526_230121-traces Viewer • Updated May 27 • 630 • 33
DCAgent3/gaia_127_rl_think_npfg_code_contests_900s_45_20260526_201919-traces Viewer • Updated May 27 • 480 • 32 • 1
DCAgent3/gaia_127_rl__24GPU_shaped__exp_rpt_pymethods2test_large__GLM_4_7_swesmith_san_3ab1d39d3 Viewer • Updated May 27 • 401 • 23
DCAgent3/gaia_127_a3_rl_SankalpKJ_nemotron_code_oracle_filtered_60_8B_20260526_201849-traces Viewer • Updated May 27 • 847 • 29
DCAgent3/gaia_127_a3_rl_DCAgent_code_contests_noblock_5_8B_20260526_201843-traces Viewer • Updated May 27 • 735 • 25
DCAgent3/gaia_127_a3_rl_DCAgent_llm_verifier_freelancer_70_8B_20260526_201846-traces Viewer • Updated May 27 • 584 • 31
DCAgent3/gaia_127_GLM_4_7_swesmith_sandboxes_with_tests_oracle_verified_120s_maxeps_131k5dec893b Viewer • Updated May 27 • 533 • 34
DCAgent3/terminal_bench_2_a3_rl_DCAgent2_nl2bash_tasks_cleaned_oracle_40_8B_20260526_1825851fc8c Viewer • Updated May 27 • 426 • 11
DCAgent3/bfcl_parity_rl__24GPU_base_excl_timeouts__exp_rpt_pymethods2test_large__GLM_4_7429ead19 Viewer • Updated May 27 • 362 • 11
DCAgent3/bfcl_parity_rl__24GPU_shaped__exp_rpt_pymethods2test_large__GLM_4_7_swesmith_sad2938994 Viewer • Updated May 27 • 370 • 9 • 1
DCAgent3/gaia_127_rl__24GPU_base_excl_timeouts__exp_rpt_pymethods2test_large__GLM_4_7_swcd44debc Viewer • Updated May 27 • 370 • 28
DCAgent3/financeagent_terminal_rl__24GPU_shaped__exp_rpt_pymethods2test_large__GLM_4_7_s9e9156c5 Viewer • Updated May 27 • 157 • 9
DCAgent3/financeagent_terminal_rl_swesmith_fixthink_pymethods2test_45_20260526_230451 Viewer • Updated May 27 • 156 • 10
DCAgent3/medagentbench_sft__pymethods2test_selfsuccess_best1_jsonfmt__laion_GLM_4_7_swes118c7735 Viewer • Updated May 27 • 1.98k • 8
DCAgent3/aider_polyglot_rl_think_npfg_code_contests_900s_45_20260526_213939 Viewer • Updated May 27 • 771 • 7
DCAgent3/financeagent_terminal_rl_think_npfg_code_contests_900s_45_20260526_230453 Viewer • Updated May 27 • 150 • 15
DCAgent3/medagentbench_rl_think_npfg_code_contests_900s_45_20260526_230734 Viewer • Updated May 27 • 1.56k • 10
DCAgent3/medagentbench_maxgn09_hint__exp_rpt_pymethods2test_large__GLM_4_7_swesmith_san_4afa9124 Viewer • Updated May 27 • 1.46k • 10
DCAgent3/aider_polyglot_a3_rl_DCAgent_exp_rpt_curriculum_easy_21_8B_20260526_230120 Viewer • Updated May 27 • 906 • 12
DCAgent3/financeagent_terminal_maxgn09_hint__exp_rpt_pymethods2test_large__GLM_4_7_swesm9c85a486 Viewer • Updated May 27 • 155 • 8
DCAgent3/financeagent_terminal_rl__24GPU_base__exp_rpt_pymethods2test_large__GLM_4_7_swe1c6107e6 Viewer • Updated May 27 • 156 • 8
DCAgent3/financeagent_terminal_rl__24GPU_base_excl_timeouts__exp_rpt_pymethods2test_largbcadf833 Viewer • Updated May 27 • 150 • 11
DCAgent3/aider_polyglot_a3_rl_DCAgent_llm_verifier_freelancer_70_8B_20260526_213904 Viewer • Updated May 27 • 780 • 11