List your company

Multi-hop Reasoning on TAT-QA

81F1 ScoreOCC-RAG-1.7B
5.49625.09844.764.302May 30, 2026

Evaluation results

MethodLinks
OCC-RAG-1.7Bthinking mode=false2026.0581
Qwen3-4Bthinking mode=true2026.0579.1
Qwen3-4Bthinking mode=false2026.0576.9
Qwen3-32Bthinking mode=true2026.0576.7
gemma-3-12b-itthinking mode=false2026.0576.5
Qwen3-32Bthinking mode=false2026.0575.9
gemma-3-27b-itthinking mode=false2026.0575.4
OCC-RAG-0.6Bthinking mode=false2026.0575
Qwen3-1.7Bthinking mode=true2026.0574.8
Qwen3-8Bthinking mode=true2026.0574.5
Qwen3-1.7Bthinking mode=false2026.0574.4
Qwen3-14Bthinking mode=true2026.0574
Qwen3-8Bthinking mode=false2026.0572.9
SmolLM3-3Bthinking mode=false2026.0571.1
Qwen3-14Bthinking mode=false2026.0570
SmolLM3-3Bthinking mode=true2026.0569.7
Qwen3-0.6Bthinking mode=true2026.0566.3
gemma-3-4b-itthinking mode=false2026.0565.3
Qwen3-0.6Bthinking mode=false2026.0562.5
gemma-3-1b-itthinking mode=false2026.0553.6
Pleias-RAG-1.2Bthinking mode=false2026.058.4