haoranli-ml/seed_1k_Qwen3-30B-Instruct-64_prefix_32k_budget_final Viewer • Updated Dec 26, 2025 • 1k • 11
haoranli-ml/POPE-hard-B_Qwen3-30B-Instruct-64_prefix_64k_budget_final Viewer • Updated Dec 25, 2025 • 440 • 46
haoranli-ml/AIME2025_Qwen3-4B-Instruct-itv0.5_rl_64_32_nokl_noentropy_8192budget_16rollouts_0.6temp Viewer • Updated Nov 25, 2025 • 30 • 7
haoranli-ml/AIME2025_Qwen3-4B-Instruct-itv0.5_rl_64_32_nokl_noentropy_4096budget_16rollouts_0.6temp Viewer • Updated Nov 25, 2025 • 30 • 6
haoranli-ml/AIME2025_Qwen3-4B-Instruct-itv0.5_rl_64_32_nokl_noentropy_16384budget_16rollouts_0.6temp Viewer • Updated Nov 24, 2025 • 30 • 6
haoranli-ml/AIME2025_Qwen3-4B-Instruct-itv0.5_rl_64_32_nokl_noentropy_32768budget_16rollouts_0.6temp Viewer • Updated Nov 24, 2025 • 30 • 8
haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_64_32_nokl_noentropy_8192budget_16rollouts_0.6temp Viewer • Updated Nov 24, 2025 • 30 • 6
haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_64_32_nokl_noentropy_4096budget_16rollouts_0.6temp Viewer • Updated Nov 24, 2025 • 30 • 6
haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_64_32_nokl_noentropy_16384budget_16rollouts_0.6temp Viewer • Updated Nov 24, 2025 • 30 • 6
haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_64_32_nokl_noentropy_32768budget_16rollouts_0.6temp Viewer • Updated Nov 24, 2025 • 30 • 6
haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_64_32_4096budget_16rollouts_0.8temp Viewer • Updated Nov 20, 2025 • 29 • 13
haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_64_32_8192budget_16rollouts_0.8temp Viewer • Updated Nov 20, 2025 • 30 • 28
haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_64_32_16384budget_16rollouts_0.8temp Viewer • Updated Nov 20, 2025 • 30 • 18
haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_64_32_32768budget_16rollouts_0.8temp Viewer • Updated Nov 20, 2025 • 30 • 14
haoranli-ml/AIME2025_Qwen3-4B-Instruct_shallow-summed-sft_rl_4096budget_16rollouts_0.8temp Viewer • Updated Nov 9, 2025 • 30 • 11
haoranli-ml/AIME2025_Qwen3-4B-Instruct_shallow-summed-sft_rl_32768budget_16rollouts_0.8temp Viewer • Updated Nov 9, 2025 • 30 • 25
haoranli-ml/AIME2025_Qwen3-4B-Instruct_shallow-summed-sft_rl_8192budget_16rollouts_0.8temp Viewer • Updated Nov 9, 2025 • 30 • 11
haoranli-ml/AIME2025_Qwen3-4B-Instruct_shallow-summed-sft_rl_16384budget_16rollouts_0.8temp Viewer • Updated Nov 9, 2025 • 30 • 13
haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_32768budget_16rollouts_0.8temp Viewer • Updated Nov 8, 2025 • 29 • 10
haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_4096budget_16rollouts_0.8temp Viewer • Updated Nov 8, 2025 • 30 • 23
haoranli-ml/AIME2025_Qwen3-4B-Instruct-raw-sft_rl_32768budget_16rollouts_0.8temp Viewer • Updated Nov 8, 2025 • 30 • 11
haoranli-ml/AIME2025_Qwen3-4B-Instruct-raw-sft_rl_4096budget_16rollouts_0.8temp Viewer • Updated Nov 8, 2025 • 30 • 18
haoranli-ml/AIME2025_Qwen3-4B-Instruct-raw-sft_rl_8192budget_16rollouts_0.8temp Viewer • Updated Nov 8, 2025 • 30 • 23
haoranli-ml/AIME2025_Qwen3-4B-Instruct-raw-sft_rl_16384budget_16rollouts_0.8temp Viewer • Updated Nov 8, 2025 • 30 • 10
haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_16384budget_16rollouts_0.8temp Viewer • Updated Nov 8, 2025 • 30 • 16