DCAgent2/dev_set_71_tasks_exp_syh_r2egym_swesmith_mixed_glm_4_7_traces_locetash_20260224_124541 Viewer • Updated Feb 25 • 210 • 12
DCAgent2/terminal_bench_2_exp_psu_stackoverflow_3K_glm_4_7_traces_20260224_062812 Viewer • Updated Feb 25 • 265 • 14
DCAgent2/dev_set_71_tasks_exp_tas_optimal_combined_traces_20260224_124603 Viewer • Updated Feb 25 • 210 • 22
DCAgent2/terminal_bench_2_GLM_4_7_swesmith_sandboxes_with_tests_oracle_verified_120s_max1f8fe289 Viewer • Updated Feb 25 • 264 • 14
DCAgent2/terminal_bench_2_exp_gfi_staqc_short_response_filtered_10K_glm_4_7_traces_locet2bda638d Viewer • Updated Feb 25 • 264 • 15
DCAgent2/dev_set_71_tasks_dev_set_part1_10k_glm_4_7_traces_locetash_20260224_124543 Viewer • Updated Feb 24 • 208 • 13
DCAgent2/dev_set_71_tasks_exp_psu_stackoverflow_316_glm_4_7_traces_20260224_124601 Viewer • Updated Feb 24 • 208 • 14
DCAgent2/terminal_bench_2_rl_bs128_gs16_rloo_n_code_contests_900s_noreg_15_20260223_182708 Viewer • Updated Feb 24 • 267 • 17
DCAgent2/dev_set_71_tasks_exp_psu_stackoverflow_10K_glm_4_7_traces_20260224_124554 Viewer • Updated Feb 24 • 209 • 15
DCAgent2/dev_set_71_tasks_bs64_rloo_n_noct_stri_micr_model_noconv_r2eg_nl2_140_20260224_124533 Viewer • Updated Feb 24 • 210 • 15
DCAgent2/dev_set_71_tasks_exp_uns_r2egym_33_6x_glm_4_7_traces_jupiter_20260224_084438 Viewer • Updated Feb 24 • 207 • 16
DCAgent2/dev_set_71_tasks_bs64_rloo_n_noct_stri_micr_model_r2eg_nl2_160_20260224_124535 Viewer • Updated Feb 24 • 210 • 14
DCAgent2/terminal_bench_2_bs64_rloo_n_noct_stri_micr_model_r2eg_nl2_160_20260223_182723 Viewer • Updated Feb 24 • 267 • 15
DCAgent2/dev_set_71_tasks_bs64_rloo_n_noct_stri_micr_auto_tis_model_r2e_100_20260224_124537 Viewer • Updated Feb 24 • 210 • 12
DCAgent2/dev_set_71_tasks_exp_psu_stackoverflow_1K_glm_4_7_traces_20260224_124558 Viewer • Updated Feb 24 • 210 • 13
DCAgent2/dev_set_71_tasks_rl_think_npfg_code_contests_900s_45_20260224_084436 Viewer • Updated Feb 24 • 204 • 15
DCAgent2/terminal_bench_2_exp_syh_r2egym_askllm_constrained_glm_4_7_traces_jupiter_202602f9a0073 Viewer • Updated Feb 24 • 262 • 16
DCAgent2/terminal_bench_2_bs64_rloo_n_noct_stri_micr_auto_tis_model_r2e_100_20260223_182725 Viewer • Updated Feb 24 • 267 • 13
DCAgent2/dev_set_71_tasks_rl_base_exp_rpt_stack_bash_90_20260224_084418 Viewer • Updated Feb 24 • 210 • 16
DCAgent2/terminal_bench_2_exp_syh_r2egym_swesmith_mixed_glm_4_7_traces_locetash_20260223_182729 Viewer • Updated Feb 24 • 267 • 15
DCAgent2/dev_set_71_tasks_GLM_4_6_stackexchange_overflow_sandboxes_32eps_65k_reasoning_n2f107446 Viewer • Updated Feb 24 • 210 • 11
DCAgent2/dev_set_71_tasks_Qwen3_8B_exp_tas_summarize_threshold_4096_traces_save_strategy6b1320f2 Viewer • Updated Feb 24 • 210 • 14
DCAgent2/dev_set_71_tasks_exp_syh_tezos_stackoverflow_mixed_glm_4_7_traces_jupiter_2026058723af1 Viewer • Updated Feb 24 • 197 • 9
DCAgent2/dev_set_71_tasks_GLM_4_7_swesmith_sandboxes_with_tests_oracle_verified_120s_max03c50f55 Viewer • Updated Feb 24 • 202 • 21
DCAgent2/dev_set_71_tasks_rl_bs128_gs16_rloo_n_code_contests_900s_noreg_15_20260224_084425 Viewer • Updated Feb 24 • 210 • 13
DCAgent2/dev_set_71_tasks_rl_base_code_contests_900s_reg_lr1e_5_140_20260224_044310 Viewer • Updated Feb 24 • 210 • 12
DCAgent2/terminal_bench_2_perturbed_docker_exp_freelancer_tasks_glm_4_7_traces_20260223_182635 Viewer • Updated Feb 24 • 266 • 13
DCAgent2/terminal_bench_2_GLM_4_6_inferredbugs_32eps_65k_fixeps_20260223_182639 Viewer • Updated Feb 24 • 267 • 13
DCAgent2/dev_set_71_tasks_exp_uns_tezos_10x_glm_4_7_traces_jupiter_20260224_044312 Viewer • Updated Feb 24 • 199 • 11