penfever/nemotron-gym-agent-workplace-v2-qwen3.5-122b-131k-opencode-traces Viewer • Updated about 3 hours ago • 296
penfever/terminal_bench_2_exp_psu_swesmith_1K_glm_4_7_traces_jupiter__6_0__Qwen3_8B_2026cb1101a1 Viewer • Updated about 13 hours ago • 2.81k • 1
penfever/terminal_bench_2_exp_psu_swesmith_1K_glm_4_7_traces_jupiter__4_0__Qwen3_8B_20264b24e003 Viewer • Updated about 13 hours ago • 2.73k • 1
penfever/nemotron-gym-if-v2-qwen3.5-122b-32k-traces Viewer • Updated about 19 hours ago • 25.2k • 7
penfever/swesmith-oracle-filtered-qwen3.5-122b-32k-traces Viewer • Updated about 19 hours ago • 864
penfever/nemotron-gym-competitive-coding-qwen3.5-122b-32k-traces Viewer • Updated 3 days ago • 11.2k • 30
penfever/nemotron-gym-if-calendar-qwen3.5-122b-32k-traces Viewer • Updated 6 days ago • 7.88k • 32
penfever/exp-rle-minimal-instructions-v3-qwen3.5-122b-32k-traces Viewer • Updated 7 days ago • 310 • 46
penfever/mix-h11-single-skill-only-v2-qwen3.5-122b-32k-traces Viewer • Updated 7 days ago • 2.8k • 44
penfever/mix-h10-reward-staged-v2-qwen3.5-122b-32k-traces Viewer • Updated 7 days ago • 3.7k • 41
penfever/mix-h10-reward-binary-v2-qwen3.5-122b-32k-traces Viewer • Updated 8 days ago • 1.5k • 51
penfever/mix-h10-reward-proportional-v2-qwen3.5-122b-32k-traces Viewer • Updated 8 days ago • 2.91k • 32
penfever/mix-h2-language-balanced-v2-qwen3.5-122b-32k-traces Viewer • Updated 8 days ago • 5.62k • 31
penfever/mix-h8-original-tests-v2-qwen3.5-122b-32k-traces Viewer • Updated 8 days ago • 2.95k • 31
penfever/mix-h1-struggle-zone-v2-qwen3.5-122b-32k-traces Viewer • Updated 9 days ago • 3.38k • 34
penfever/methods2test-large-v2-qwen3.5-122b-32k-traces Viewer • Updated 12 days ago • 4.9k • 34
penfever/pymethods2test-large-qwen3.5-122b-32k-traces Viewer • Updated 14 days ago • 4.67k • 87 • 1
penfever/nemotron-math-oracle-filtered-qwen3.5-122b-32k-traces Viewer • Updated 14 days ago • 13.8k • 126
penfever/swe_rebench_patched_oracle-minimax-m27-131k-traces_chunk2 Viewer • Updated 14 days ago • 500 • 29