List your company

Agentic Search Benchmarks Average

58Average Token-level F1PDA-GAM
44.68848.14451.655.056May 29, 2026

Evaluation results

MethodLinks
PDA-GAMStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=42026.0558
PDA-TIESStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=42026.0557.4
PDA-GAMStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=32026.0557.4
PDA-TIESStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=32026.0557.1
PDA-AveragingStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=42026.0556.9
PDA-KnOTSStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=42026.0556.8
PDA-GAMStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=42026.0556.2
PDA-TIESStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=42026.0556
PDA-GAMStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=32026.0555.9
PDA-AveragingStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=42026.0555.7
PDA-TIESStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=32026.0555.7
PDA-TIESStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=22026.0555.5
PDA-KnOTSStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=42026.0555.5
PDA-GAMStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=22026.0554.8
PDA-TIESStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=22026.0554.3
Search-R1Student Model=Qwen3-8B, Number of Preference Deltas (∆)=12026.0553.7
PDA-GAMStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=22026.0553.7
Qwen3Student Model=Qwen3-8B, Number of Preference Deltas (∆)=12026.0552.9
Joint ORPOStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=42026.0552.8
Search-R1Student Model=Tülu3-8B, Number of Preference Deltas (∆)=12026.0552.3
AceSearcherStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=12026.0551.9
Joint ORPOStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=42026.0551.7
Qwen3Student Model=Tülu3-8B, Number of Preference Deltas (∆)=12026.0551.3
Llama-3.2Student Model=Qwen3-8B, Number of Preference Deltas (∆)=12026.0550.9
Student BaselineStudent Model=Qwen3-8B2026.0550.7
AceSearcherStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=12026.0550.3
Llama-3.2Student Model=Tülu3-8B, Number of Preference Deltas (∆)=12026.0549.2
Student BaselineStudent Model=Tülu3-8B2026.0548.7
Sequential ORPOStudent Model=Qwen3-8B, Number of Preference Deltas (∆)=22026.0547.9
Sequential ORPOStudent Model=Tülu3-8B, Number of Preference Deltas (∆)=22026.0545.2