AutoRSE-Leaderboard / leaderboard-data.csv
Ray0311's picture
Upload 4 files
9399452 verified
Raw History Blame Contribute Delete
7.27 kB
configuration_id,harness,model,provenance,task,metric,baseline_score,mean_score,score_sd,relative_gain_percent,average_gain_percent,performance_trials,source_url,task_rank,rank_sum,mean_task_rank,overall_rank
claude-code-deepseek-v4-flash,Claude Code,DeepSeek V4 Flash,Paper reference,HSTU,NDCG@10,0.0535,0.0674,0.0032,25.98,13.01,3,https://arxiv.org/abs/2610.37228,3,21,3.5,3
claude-code-deepseek-v4-flash,Claude Code,DeepSeek V4 Flash,Paper reference,IntSR,Macro NDCG@10,0.6940,0.6606,0.0541,-4.81,13.01,3,https://arxiv.org/abs/2610.37228,4,21,3.5,3
claude-code-deepseek-v4-flash,Claude Code,DeepSeek V4 Flash,Paper reference,TIGER,NDCG@10,0.0332,0.0476,0.0138,43.37,13.01,3,https://arxiv.org/abs/2610.37228,6,21,3.5,3
claude-code-deepseek-v4-flash,Claude Code,DeepSeek V4 Flash,Paper reference,OneTrans,Click AUC,0.6767,0.7467,0.0324,10.34,13.01,3,https://arxiv.org/abs/2610.37228,1,21,3.5,3
claude-code-deepseek-v4-flash,Claude Code,DeepSeek V4 Flash,Paper reference,RankMixer,AUC,0.7859,0.7979,0.0015,1.53,13.01,3,https://arxiv.org/abs/2610.37228,3,21,3.5,3
claude-code-deepseek-v4-flash,Claude Code,DeepSeek V4 Flash,Paper reference,WuKong,AUC,0.9645,0.9805,0.0030,1.66,13.01,3,https://arxiv.org/abs/2610.37228,4,21,3.5,3
claude-code-claude-opus-4-8,Claude Code,Claude Opus 4.8,Paper reference,HSTU,NDCG@10,0.0535,0.0754,0.0043,40.93,24.42,3,https://arxiv.org/abs/2610.37228,1,14,2.33333333333,1
claude-code-claude-opus-4-8,Claude Code,Claude Opus 4.8,Paper reference,IntSR,Macro NDCG@10,0.6940,0.7325,0.0292,5.55,24.42,3,https://arxiv.org/abs/2610.37228,2,14,2.33333333333,1
claude-code-claude-opus-4-8,Claude Code,Claude Opus 4.8,Paper reference,TIGER,NDCG@10,0.0332,0.0631,0.0164,90.06,24.42,3,https://arxiv.org/abs/2610.37228,2,14,2.33333333333,1
claude-code-claude-opus-4-8,Claude Code,Claude Opus 4.8,Paper reference,OneTrans,Click AUC,0.6767,0.7184,0.0068,6.16,24.42,3,https://arxiv.org/abs/2610.37228,6,14,2.33333333333,1
claude-code-claude-opus-4-8,Claude Code,Claude Opus 4.8,Paper reference,RankMixer,AUC,0.7859,0.8002,0.0009,1.82,24.42,3,https://arxiv.org/abs/2610.37228,1,14,2.33333333333,1
claude-code-claude-opus-4-8,Claude Code,Claude Opus 4.8,Paper reference,WuKong,AUC,0.9645,0.9840,0.0039,2.02,24.42,3,https://arxiv.org/abs/2610.37228,2,14,2.33333333333,1
codex-deepseek-v4-flash,Codex,DeepSeek V4 Flash,Paper reference,HSTU,NDCG@10,0.0535,0.0657,0.0030,22.80,16.88,3,https://arxiv.org/abs/2610.37228,6,31,5.16666666667,7
codex-deepseek-v4-flash,Codex,DeepSeek V4 Flash,Paper reference,IntSR,Macro NDCG@10,0.6940,0.6485,0.0335,-6.56,16.88,3,https://arxiv.org/abs/2610.37228,5,31,5.16666666667,7
codex-deepseek-v4-flash,Codex,DeepSeek V4 Flash,Paper reference,TIGER,NDCG@10,0.0332,0.0583,0.0147,75.60,16.88,3,https://arxiv.org/abs/2610.37228,4,31,5.16666666667,7
codex-deepseek-v4-flash,Codex,DeepSeek V4 Flash,Paper reference,OneTrans,Click AUC,0.6767,0.7203,0.0044,6.44,16.88,3,https://arxiv.org/abs/2610.37228,5,31,5.16666666667,7
codex-deepseek-v4-flash,Codex,DeepSeek V4 Flash,Paper reference,RankMixer,AUC,0.7859,0.7974,0.0003,1.46,16.88,3,https://arxiv.org/abs/2610.37228,5,31,5.16666666667,7
codex-deepseek-v4-flash,Codex,DeepSeek V4 Flash,Paper reference,WuKong,AUC,0.9645,0.9790,0.0018,1.50,16.88,3,https://arxiv.org/abs/2610.37228,6,31,5.16666666667,7
codex-gpt-5-5,Codex,GPT-5.5,Paper reference,HSTU,NDCG@10,0.0535,0.0672,0.0065,25.61,24.24,3,https://arxiv.org/abs/2610.37228,4,19,3.16666666667,2
codex-gpt-5-5,Codex,GPT-5.5,Paper reference,IntSR,Macro NDCG@10,0.6940,0.7692,0.1904,10.84,24.24,3,https://arxiv.org/abs/2610.37228,1,19,3.16666666667,2
codex-gpt-5-5,Codex,GPT-5.5,Paper reference,TIGER,NDCG@10,0.0332,0.0659,0.0046,98.49,24.24,3,https://arxiv.org/abs/2610.37228,1,19,3.16666666667,2
codex-gpt-5-5,Codex,GPT-5.5,Paper reference,OneTrans,Click AUC,0.6767,0.7292,0.0342,7.76,24.24,3,https://arxiv.org/abs/2610.37228,2,19,3.16666666667,2
codex-gpt-5-5,Codex,GPT-5.5,Paper reference,RankMixer,AUC,0.7859,0.7954,0.0030,1.21,24.24,3,https://arxiv.org/abs/2610.37228,6,19,3.16666666667,2
codex-gpt-5-5,Codex,GPT-5.5,Paper reference,WuKong,AUC,0.9645,0.9796,0.0032,1.57,24.24,3,https://arxiv.org/abs/2610.37228,5,19,3.16666666667,2
terminus-2-deepseek-v4-flash,Terminus-2,DeepSeek V4 Flash,Paper reference,HSTU,NDCG@10,0.0535,0.0667,0.0057,24.67,14.10,3,https://arxiv.org/abs/2610.37228,5,28,4.66666666667,5
terminus-2-deepseek-v4-flash,Terminus-2,DeepSeek V4 Flash,Paper reference,IntSR,Macro NDCG@10,0.6940,0.6291,0.0858,-9.35,14.10,3,https://arxiv.org/abs/2610.37228,6,28,4.66666666667,5
terminus-2-deepseek-v4-flash,Terminus-2,DeepSeek V4 Flash,Paper reference,TIGER,NDCG@10,0.0332,0.0554,0.0158,66.87,14.10,3,https://arxiv.org/abs/2610.37228,5,28,4.66666666667,5
terminus-2-deepseek-v4-flash,Terminus-2,DeepSeek V4 Flash,Paper reference,OneTrans,Click AUC,0.6767,0.6665,0.0447,-1.51,14.10,3,https://arxiv.org/abs/2610.37228,7,28,4.66666666667,5
terminus-2-deepseek-v4-flash,Terminus-2,DeepSeek V4 Flash,Paper reference,RankMixer,AUC,0.7859,0.7977,0.0012,1.50,14.10,3,https://arxiv.org/abs/2610.37228,4,28,4.66666666667,5
terminus-2-deepseek-v4-flash,Terminus-2,DeepSeek V4 Flash,Paper reference,WuKong,AUC,0.9645,0.9877,0.0020,2.41,14.10,3,https://arxiv.org/abs/2610.37228,1,28,4.66666666667,5
terminus-2-gpt-5-5,Terminus-2,GPT-5.5,Paper reference,HSTU,NDCG@10,0.0535,0.0697,0.0058,30.28,18.93,3,https://arxiv.org/abs/2610.37228,2,29,4.83333333333,6
terminus-2-gpt-5-5,Terminus-2,GPT-5.5,Paper reference,IntSR,Macro NDCG@10,0.6940,0.6146,0.0711,-11.44,18.93,3,https://arxiv.org/abs/2610.37228,7,29,4.83333333333,6
terminus-2-gpt-5-5,Terminus-2,GPT-5.5,Paper reference,TIGER,NDCG@10,0.0332,0.0614,0.0053,84.94,18.93,3,https://arxiv.org/abs/2610.37228,3,29,4.83333333333,6
terminus-2-gpt-5-5,Terminus-2,GPT-5.5,Paper reference,OneTrans,Click AUC,0.6767,0.7285,0.0498,7.65,18.93,2,https://arxiv.org/abs/2610.37228,3,29,4.83333333333,6
terminus-2-gpt-5-5,Terminus-2,GPT-5.5,Paper reference,RankMixer,AUC,0.7859,0.7944,0.0021,1.08,18.93,3,https://arxiv.org/abs/2610.37228,7,29,4.83333333333,6
terminus-2-gpt-5-5,Terminus-2,GPT-5.5,Paper reference,WuKong,AUC,0.9645,0.9749,0.0035,1.08,18.93,3,https://arxiv.org/abs/2610.37228,7,29,4.83333333333,6
terminus-2-claude-opus-4-8,Terminus-2,Claude Opus 4.8,Paper reference,HSTU,NDCG@10,0.0535,0.0636,0.0015,18.88,1.42,3,https://arxiv.org/abs/2610.37228,7,26,4.33333333333,4
terminus-2-claude-opus-4-8,Terminus-2,Claude Opus 4.8,Paper reference,IntSR,Macro NDCG@10,0.6940,0.6761,0.0334,-2.58,1.42,3,https://arxiv.org/abs/2610.37228,3,26,4.33333333333,4
terminus-2-claude-opus-4-8,Terminus-2,Claude Opus 4.8,Paper reference,TIGER,NDCG@10,0.0332,0.0273,0.0190,-17.77,1.42,3,https://arxiv.org/abs/2610.37228,7,26,4.33333333333,4
terminus-2-claude-opus-4-8,Terminus-2,Claude Opus 4.8,Paper reference,OneTrans,Click AUC,0.6767,0.7207,0.0232,6.50,1.42,3,https://arxiv.org/abs/2610.37228,4,26,4.33333333333,4
terminus-2-claude-opus-4-8,Terminus-2,Claude Opus 4.8,Paper reference,RankMixer,AUC,0.7859,0.7989,0.0014,1.65,1.42,3,https://arxiv.org/abs/2610.37228,2,26,4.33333333333,4
terminus-2-claude-opus-4-8,Terminus-2,Claude Opus 4.8,Paper reference,WuKong,AUC,0.9645,0.9823,0.0004,1.85,1.42,3,https://arxiv.org/abs/2610.37228,3,26,4.33333333333,4