InferenceNet-Leaderboard / leaderboard.csv
YICHEN013's picture lry520111's picture
Add DeepSeek API + DSH results and independent leaderboard entry (#6)
50f656f
Raw History Blame Contribute Delete
11.2 kB
model,arm,harness,metric_profile,metric,successes,denominator,unknown,score_percent,official_parity_verified,source_revision,display_name,comparison_group,underlying_model_weights_verified
gpt-5.6-sol,baseline,none,local-paper-v1,perfect,338,1000,445,33.8,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,GPT-5.6 Sol,historical_pair,
gpt-5.6-sol,baseline,none,hf-leaderboard-v1,compilation_success,557,1000,3,55.7,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,GPT-5.6 Sol,historical_pair,
gpt-5.6-sol,baseline,none,hf-leaderboard-v1,partial_replication,430,1000,444,43.0,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,GPT-5.6 Sol,historical_pair,
gpt-5.6-sol,baseline,none,hf-leaderboard-v1,coefficient_direction,537,1000,444,53.7,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,GPT-5.6 Sol,historical_pair,
gpt-5.6-sol,baseline,none,hf-leaderboard-v1,significance_level,485,1000,444,48.5,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,GPT-5.6 Sol,historical_pair,
gpt-5.6-sol,deepagents,DeepAgents,local-paper-v1,perfect,518,1000,95,51.8,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,GPT-5.6 Sol,historical_pair,
gpt-5.6-sol,deepagents,DeepAgents,hf-leaderboard-v1,compilation_success,910,1000,10,91.0,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,GPT-5.6 Sol,historical_pair,
gpt-5.6-sol,deepagents,DeepAgents,hf-leaderboard-v1,partial_replication,699,1000,92,69.9,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,GPT-5.6 Sol,historical_pair,
gpt-5.6-sol,deepagents,DeepAgents,hf-leaderboard-v1,coefficient_direction,879,1000,92,87.9,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,GPT-5.6 Sol,historical_pair,
gpt-5.6-sol,deepagents,DeepAgents,hf-leaderboard-v1,significance_level,787,1000,93,78.7,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,GPT-5.6 Sol,historical_pair,
claude-opus-4-8,baseline,none,local-paper-v1,perfect,184,1000,538,18.4,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Claude Opus 4.8,historical_pair,
claude-opus-4-8,baseline,none,hf-leaderboard-v1,compilation_success,467,1000,0,46.7,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Claude Opus 4.8,historical_pair,
claude-opus-4-8,baseline,none,hf-leaderboard-v1,partial_replication,305,1000,537,30.5,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Claude Opus 4.8,historical_pair,
claude-opus-4-8,baseline,none,hf-leaderboard-v1,coefficient_direction,437,1000,537,43.7,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Claude Opus 4.8,historical_pair,
claude-opus-4-8,baseline,none,hf-leaderboard-v1,significance_level,370,1000,537,37.0,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Claude Opus 4.8,historical_pair,
claude-opus-4-8,deepagents,DeepAgents,local-paper-v1,perfect,392,1000,174,39.2,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Claude Opus 4.8,historical_pair,
claude-opus-4-8,deepagents,DeepAgents,hf-leaderboard-v1,compilation_success,834,1000,4,83.4,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Claude Opus 4.8,historical_pair,
claude-opus-4-8,deepagents,DeepAgents,hf-leaderboard-v1,partial_replication,621,1000,170,62.1,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Claude Opus 4.8,historical_pair,
claude-opus-4-8,deepagents,DeepAgents,hf-leaderboard-v1,coefficient_direction,793,1000,170,79.3,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Claude Opus 4.8,historical_pair,
claude-opus-4-8,deepagents,DeepAgents,hf-leaderboard-v1,significance_level,696,1000,172,69.6,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Claude Opus 4.8,historical_pair,
kimi-k3,baseline,none,local-paper-v1,perfect,230,1000,481,23.0,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Kimi K3,historical_pair,
kimi-k3,baseline,none,hf-leaderboard-v1,compilation_success,526,1000,5,52.6,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Kimi K3,historical_pair,
kimi-k3,baseline,none,hf-leaderboard-v1,partial_replication,366,1000,481,36.6,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Kimi K3,historical_pair,
kimi-k3,baseline,none,hf-leaderboard-v1,coefficient_direction,494,1000,481,49.4,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Kimi K3,historical_pair,
kimi-k3,baseline,none,hf-leaderboard-v1,significance_level,431,1000,481,43.1,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Kimi K3,historical_pair,
kimi-k3,deepagents,DeepAgents 0.7.13,local-paper-v1,perfect,390,1000,159,39.0,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Kimi K3,historical_pair,
kimi-k3,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,compilation_success,867,1000,4,86.7,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Kimi K3,historical_pair,
kimi-k3,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,partial_replication,635,1000,156,63.5,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Kimi K3,historical_pair,
kimi-k3,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,coefficient_direction,804,1000,156,80.4,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Kimi K3,historical_pair,
kimi-k3,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,significance_level,709,1000,157,70.9,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Kimi K3,historical_pair,
gemini-3.1-pro-preview,baseline,none,local-paper-v1,perfect,246,1000,462,24.6,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Gemini 3.1 Pro Preview,historical_pair,
gemini-3.1-pro-preview,baseline,none,hf-leaderboard-v1,compilation_success,543,1000,0,54.3,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Gemini 3.1 Pro Preview,historical_pair,
gemini-3.1-pro-preview,baseline,none,hf-leaderboard-v1,partial_replication,366,1000,460,36.6,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Gemini 3.1 Pro Preview,historical_pair,
gemini-3.1-pro-preview,baseline,none,hf-leaderboard-v1,coefficient_direction,506,1000,460,50.6,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Gemini 3.1 Pro Preview,historical_pair,
gemini-3.1-pro-preview,baseline,none,hf-leaderboard-v1,significance_level,437,1000,460,43.7,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Gemini 3.1 Pro Preview,historical_pair,
gemini-3.1-pro-preview,deepagents,DeepAgents 0.7.13,local-paper-v1,perfect,391,1000,155,39.1,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Gemini 3.1 Pro Preview,historical_pair,
gemini-3.1-pro-preview,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,compilation_success,850,1000,0,85.0,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Gemini 3.1 Pro Preview,historical_pair,
gemini-3.1-pro-preview,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,partial_replication,632,1000,153,63.2,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Gemini 3.1 Pro Preview,historical_pair,
gemini-3.1-pro-preview,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,coefficient_direction,811,1000,153,81.1,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Gemini 3.1 Pro Preview,historical_pair,
gemini-3.1-pro-preview,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,significance_level,718,1000,154,71.8,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Gemini 3.1 Pro Preview,historical_pair,
qwen3.7-max,baseline,none,local-paper-v1,perfect,198,1000,519,19.8,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Qwen3.7-Max,historical_pair,
qwen3.7-max,baseline,none,hf-leaderboard-v1,compilation_success,486,1000,0,48.6,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Qwen3.7-Max,historical_pair,
qwen3.7-max,baseline,none,hf-leaderboard-v1,partial_replication,315,1000,518,31.5,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Qwen3.7-Max,historical_pair,
qwen3.7-max,baseline,none,hf-leaderboard-v1,coefficient_direction,454,1000,518,45.4,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Qwen3.7-Max,historical_pair,
qwen3.7-max,baseline,none,hf-leaderboard-v1,significance_level,396,1000,518,39.6,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Qwen3.7-Max,historical_pair,
qwen3.7-max,deepagents,DeepAgents 0.7.13,local-paper-v1,perfect,248,1000,481,24.8,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Qwen3.7-Max,historical_pair,
qwen3.7-max,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,compilation_success,523,1000,7,52.3,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Qwen3.7-Max,historical_pair,
qwen3.7-max,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,partial_replication,379,1000,481,37.9,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Qwen3.7-Max,historical_pair,
qwen3.7-max,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,coefficient_direction,488,1000,481,48.8,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Qwen3.7-Max,historical_pair,
qwen3.7-max,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,significance_level,433,1000,481,43.3,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,Qwen3.7-Max,historical_pair,
deepseek-v4-pro,baseline,none,local-paper-v1,perfect,129,1000,723,12.9,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek V4 Pro,historical_pair,
deepseek-v4-pro,baseline,none,hf-leaderboard-v1,compilation_success,281,1000,0,28.1,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek V4 Pro,historical_pair,
deepseek-v4-pro,baseline,none,hf-leaderboard-v1,partial_replication,195,1000,723,19.5,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek V4 Pro,historical_pair,
deepseek-v4-pro,baseline,none,hf-leaderboard-v1,coefficient_direction,260,1000,723,26.0,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek V4 Pro,historical_pair,
deepseek-v4-pro,baseline,none,hf-leaderboard-v1,significance_level,236,1000,723,23.6,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek V4 Pro,historical_pair,
deepseek-v4-pro,deepagents,DeepAgents 0.7.13,local-paper-v1,perfect,183,1000,648,18.3,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek V4 Pro,historical_pair,
deepseek-v4-pro,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,compilation_success,352,1000,0,35.2,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek V4 Pro,historical_pair,
deepseek-v4-pro,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,partial_replication,270,1000,648,27.0,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek V4 Pro,historical_pair,
deepseek-v4-pro,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,coefficient_direction,338,1000,648,33.8,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek V4 Pro,historical_pair,
deepseek-v4-pro,deepagents,DeepAgents 0.7.13,hf-leaderboard-v1,significance_level,308,1000,648,30.8,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek V4 Pro,historical_pair,
deepseek-v4-pro,dsh,DeepSeek Harness SDK 0.1.5rc1,local-paper-v1,perfect,372,1000,305,37.2,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek API [v4-pro alias] + DSH,independent,False
deepseek-v4-pro,dsh,DeepSeek Harness SDK 0.1.5rc1,hf-leaderboard-v1,compilation_success,699,1000,30,69.9,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek API [v4-pro alias] + DSH,independent,False
deepseek-v4-pro,dsh,DeepSeek Harness SDK 0.1.5rc1,hf-leaderboard-v1,partial_replication,556,1000,302,55.6,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek API [v4-pro alias] + DSH,independent,False
deepseek-v4-pro,dsh,DeepSeek Harness SDK 0.1.5rc1,hf-leaderboard-v1,coefficient_direction,683,1000,302,68.3,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek API [v4-pro alias] + DSH,independent,False
deepseek-v4-pro,dsh,DeepSeek Harness SDK 0.1.5rc1,hf-leaderboard-v1,significance_level,598,1000,304,59.8,False,6ea7c5684664bfe5c6e3d282a5e28f68244acd9e,DeepSeek API [v4-pro alias] + DSH,independent,False