DCAgent3/terminal_bench_2_ablation_pymethods2test_seqmean_arm0_tis_15_8B_20260612_171537 Viewer • Updated Jun 12 • 540 • 18
DCAgent3/terminal_bench_2_ablation_pymethods2test_shaped_45_8B_20260612_171528 Viewer • Updated Jun 12 • 439 • 20
DCAgent3/dev_set_v2_ablation_pymethods2test_shaped_45_8B_20260612_114851 Viewer • Updated Jun 12 • 330 • 16
DCAgent3/dev_set_v2_ablation_pymethods2test_seqmean_arm0_30_8B_20260612_114936 Viewer • Updated Jun 12 • 379 • 16
DCAgent3/dev_set_v2_ablation_pymethods2test_seqnorm_15_8B_20260612_115028 Viewer • Updated Jun 12 • 337 • 15
DCAgent3/dev_set_v2_ablation_pymethods2test_seqmean_arm0_tis_15_8B_20260612_115056 Viewer • Updated Jun 12 • 385 • 14
DCAgent3/gaia_127_a3_rl_SankalpKJ_swesmith_oracle_filtered_40_8B_20260612_025544-traces Viewer • Updated Jun 12 • 603 • 24
DCAgent3/swebench_verified_random_100_folders_a3_rl_SankalpKJ_swesmith_oracle_filtered_4746380e4 Viewer • Updated Jun 12 • 546 • 16
DCAgent3/swebench_verified_a3_rl_laion_exp_rpt_codenet_python_v2_20260606_225850 Viewer • Updated Jun 12 • 2.07k • 166
DCAgent3/swebench_verified_g1_diverse_tezos_top4_100k_8b_20260610_231527 Viewer • Updated Jun 12 • 4.1k • 17
DCAgent3/swebench_verified_a3_rl_DCAgent_exp_rpt_pymethods2test_v3_10_8B_20260606_092003 Viewer • Updated Jun 12 • 2.83k • 18
DCAgent3/financeagent_terminal_a3_rl_SankalpKJ_swesmith_oracle_filtered_40_8B_20260612_025710 Viewer • Updated Jun 12 • 167 • 24
DCAgent3/dev_set_v2_a3_rl_SankalpKJ_swesmith_oracle_filtered_40_8B_20260612_025505 Viewer • Updated Jun 12 • 370 • 18
DCAgent3/medagentbench_a3_rl_SankalpKJ_swesmith_oracle_filtered_40_8B_20260612_025702 Viewer • Updated Jun 12 • 1.6k • 23
DCAgent3/terminal_bench_2_a3_rl_SankalpKJ_swesmith_oracle_filtered_40_8B_20260612_025521 Viewer • Updated Jun 12 • 451 • 24
DCAgent3/bfcl_parity_a3_rl_SankalpKJ_swesmith_oracle_filtered_40_8B_20260612_025536 Viewer • Updated Jun 12 • 374 • 12
DCAgent3/swebench_verified_random_100_folders_g1_diverse_tezos_top4_100k_8b_20260610_110634 Viewer • Updated Jun 11 • 728 • 14
DCAgent3/gaia_127_g1_diverse_tezos_top4_100k_8b_20260610_110704-traces Viewer • Updated Jun 11 • 601 • 18
DCAgent3/gaia_127_a3_rl_DCAgent_r2egym_patched_full_oracle_75_8B_20260610_105535-traces Viewer • Updated Jun 11 • 605 • 24
DCAgent3/swebench_verified_a3_rl_DCAgent_r2egym_patched_full_oracle_75_8B_20260610_105709 Viewer • Updated Jun 11 • 3.51k • 30
DCAgent3/swebench_verified_random_100_folders_a3_rl_DCAgent_r2egym_patched_full_oracle_7d75ed630 Viewer • Updated Jun 11 • 677 • 26
DCAgent3/swebench_verified_random_100_folders_g1_diverse_tezos_top4_100k_8b_20260610_231352 Viewer • Updated Jun 11 • 716 • 13
DCAgent3/financeagent_terminal_g1_diverse_tezos_top4_100k_8b_20260610_231518 Viewer • Updated Jun 10 • 172 • 13
DCAgent3/bfcl_parity_g1_diverse_tezos_top4_100k_8b_20260610_231510 Viewer • Updated Jun 10 • 369 • 12
DCAgent3/bfcl_parity_a3_rl_DCAgent_r2egym_patched_full_oracle_75_8B_20260610_231344 Viewer • Updated Jun 10 • 369 • 13
DCAgent3/aider_polyglot_a3_rl_DCAgent_r2egym_patched_full_oracle_75_8B_20260610_105520 Viewer • Updated Jun 10 • 801 • 16
DCAgent3/aider_polyglot_g1_diverse_tezos_top4_100k_8b_20260610_110649 Viewer • Updated Jun 10 • 931 • 17
DCAgent3/medagentbench_a3_rl_DCAgent_r2egym_patched_full_oracle_75_8B_20260610_105653 Viewer • Updated Jun 10 • 1.21k • 19
DCAgent3/terminal_bench_2_a3_rl_DCAgent_r2egym_patched_full_oracle_75_8B_20260610_105512 Viewer • Updated Jun 10 • 522 • 26
DCAgent3/medagentbench_g1_diverse_tezos_top4_100k_8b_20260610_110822 Viewer • Updated Jun 10 • 1.31k • 18