Share your thoughts, 1 month free Claude Pro on usSee more

Multi-hop Reasoning on TAT-QA

81F1 Score

OCC-RAG-1.7B

Updated 1d ago

Evaluation Results

Method	Links
OCC-RAG-1.7B 2026.05		81
Qwen3-4B 2026.05		79.1
Qwen3-4B 2026.05		76.9
Qwen3-32B 2026.05		76.7
gemma-3-12b-it 2026.05		76.5
Qwen3-32B 2026.05		75.9
gemma-3-27b-it 2026.05		75.4
OCC-RAG-0.6B 2026.05		75
Qwen3-1.7B 2026.05		74.8
Qwen3-8B 2026.05		74.5
Qwen3-1.7B 2026.05		74.4
Qwen3-14B 2026.05		74
Qwen3-8B 2026.05		72.9
SmolLM3-3B 2026.05		71.1
Qwen3-14B 2026.05		70
SmolLM3-3B 2026.05		69.7
Qwen3-0.6B 2026.05		66.3
gemma-3-4b-it 2026.05		65.3
Qwen3-0.6B 2026.05		62.5
gemma-3-1b-it 2026.05		53.6
Pleias-RAG-1.2B 2026.05		8.4