List your company

Retrieval on retrieval benchmark (hold-out)

84Hit Rate @ 5GPT-5.4
46.5656.286675.72Jul 1, 2026

Evaluation results

MethodLinks
GPT-5.4Turns=M, Tool Setup=Web Search + Toolset2026.07848789.556.871.841.643.85.610.1508
Qwen3.5-397BTurns=M, Tool Setup=Workflow2026.07828586.542.167.935.53612.51.220.0657
GPT-5.4Turns=1, Tool Setup=Web Search + Toolset2026.0779.58284.553.562.837.139.42.61.070.3115
GPT-5.4Turns=M, Tool Setup=Web Search2026.07798589.548.265.335.337.55.610.1404
Qwen3.5-397BTurns=M, Tool Setup=Toolset2026.0778.588.591.548.662.13841.67.31.070.1082
PAPERPILOT-9BTurns=M, Tool Setup=Workflow + Toolset2026.077783.589.54059.432.535.442.81.660.018
Qwen3.5-397BTurns=1, Tool Setup=Toolset2026.07748789.543.257.834.13715.71.670.047
GPT-5.4Turns=1, Tool Setup=Web Search2026.0772.579814460.233.535.4210.3703
o4-mini DeepResearchTurns=1*, Tool Setup=Web Search2026.077281.584.546.35329.231.70.10.476.0903
Qwen3.5-397BTurns=1, Tool Setup=Workflow2026.0770788241.153.628.429.7301.970.0233
Qwen3.5-9BTurns=1, Tool Setup=Toolset2026.07698285.538.356.531.233.4168.33.030.0041
Qwen3.5-9BTurns=M, Tool Setup=Toolset2026.07587175.534.847.526.82943.31.670.0134
GPT-5.4Turns=M, Tool Setup=Workflow2026.0756.5788453.638.220.5242.50.820.2231
GPT-5.4Turns=1, Tool Setup=Workflow2026.0752708354.136.418.822.12.91.10.1803
Qwen3.5-9BTurns=1, Tool Setup=Workflow2026.0748.566.57753.731.217.421.51472.930.0033
Qwen3.5-9BTurns=M, Tool Setup=Workflow2026.074867.57552.632.717.420.488.920.0054