Table Question Answering on NQ-Table
80.1F1 ScoreQUIETT
Evaluation Results
| Method | Links | |
|---|---|---|
| QUIETTCategory=Agentic, Model=Gemini 2.52026.02 | 80.1 | |
| QUIETTCategory=Agentic, Model=DeepSeek V3.12026.02 | 79.2 | |
| QUIETTCategory=Agentic, Model=Gemini 2.02026.02 | 73.25 | |
| EEDPCategory=Direct, Model=Gemini 2.52026.02 | 72.79 | |
| QUIETTCategory=Agentic, Model=GPT-OSS2026.02 | 72.75 | |
| QUIETTCategory=Agentic, Model=Qwen 32026.02 | 72.6 | |
| EEDPCategory=Direct, Model=DeepSeek V3.12026.02 | 72.29 | |
| EEDPCategory=Direct, Model=GPT-OSS2026.02 | 71.8 | |
| CoTCategory=Direct, Model=Gemini 2.52026.02 | 71.22 | |
| EEDPCategory=Direct, Model=Gemini 2.02026.02 | 70.31 | |
| Chain of TablesCategory=Agentic, Model=DeepSeek V3.12026.02 | 70.1 | |
| Chain of TablesCategory=Agentic, Model=Gemini 2.52026.02 | 69.56 | |
| CoTCategory=Direct, Model=Gemini 2.02026.02 | 68.7 | |
| CRAFTLLM Backbone=GPT-4o, n=52025.05 | 67.72 | |
| POTCategory=Agentic, Model=Gemini 2.52026.02 | 67.7 | |
| BinderCategory=Direct, Model=DeepSeek V3.12026.02 | 67.44 | |
| BinderCategory=Direct, Model=Gemini 2.52026.02 | 67.24 | |
| CoTCategory=Direct, Model=GPT-OSS2026.02 | 66.6 | |
| BinderCategory=Direct, Model=GPT-OSS2026.02 | 66.5 | |
| POTCategory=Agentic, Model=DeepSeek V3.12026.02 | 65.33 | |
| Chain of TablesCategory=Agentic, Model=Qwen 32026.02 | 64.33 | |
| CoTCategory=Direct, Model=DeepSeek V3.12026.02 | 63.6 | |
| Chain of TablesCategory=Agentic, Model=Gemini 2.02026.02 | 62.3 | |
| BinderCategory=Direct, Model=Gemini 2.02026.02 | 62.25 | |
| EEDPCategory=Direct, Model=Qwen 32026.02 | 62.21 | |
| POTCategory=Agentic, Model=Qwen 32026.02 | 62.1 | |
| POTCategory=Agentic, Model=Gemini 2.02026.02 | 61.7 | |
| BinderCategory=Direct, Model=Qwen 32026.02 | 61.56 | |
| CoTCategory=Direct, Model=Qwen 32026.02 | 61.34 | |
| Chain of TablesCategory=Agentic, Model=GPT-OSS2026.02 | 60.21 | |
| POTCategory=Agentic, Model=GPT-OSS2026.02 | 57.6 | |
| CRAFTLLM Backbone=Mistral-Small-Instruct, n=52025.05 | 57.14 | |
| TableSQLifyCategory=Direct, Model=DeepSeek V3.12026.02 | 56.94 | |
| CRAFTLLM Backbone=Llama-3.1-70B-Instruct, n=52025.05 | 56.94 | |
| CRAFTLLM Backbone=GPT-4o, n=12025.05 | 56.76 | |
| E5Category=Direct, Model=Gemini 2.52026.02 | 55.9 | |
| NormTabCategory=Direct, Model=DeepSeek V3.12026.02 | 55.4 | |
| CRAFTLLM Backbone=Llama-3.3-70B-Instruct, n=52025.05 | 55.16 | |
| E5Category=Direct, Model=DeepSeek V3.12026.02 | 54.55 | |
| LI-RAGEn=52025.05 | 54.17 | |
| E5Category=Direct, Model=GPT-OSS2026.02 | 54 | |
| E5Category=Direct, Model=Qwen 32026.02 | 53.16 | |
| NormTabCategory=Direct, Model=Gemini 2.52026.02 | 53 | |
| NormTabCategory=Direct, Model=Gemini 2.02026.02 | 51.8 | |
| TableSQLifyCategory=Direct, Model=Qwen 32026.02 | 51.34 | |
| NormTabCategory=Direct, Model=GPT-OSS2026.02 | 50.3 | |
| CRAFTLLM Backbone=Mistral-Small-Instruct, n=12025.05 | 50.26 | |
| CRAFTLLM Backbone=Llama-3.1-70B-Instruct, n=12025.05 | 49.75 | |
| DPR-RAGEn=52025.05 | 49.68 | |
| CRAFTLLM Backbone=Qwen2.5-72B-Instruct, n=52025.05 | 49.17 | |
| CRAFTLLM Backbone=Qwen2.5-72B-Instruct, n=12025.05 | 48.75 | |
| E5Category=Direct, Model=Gemini 2.02026.02 | 48.4 | |
| CoT + SQLCategory=Direct, Model=GPT-OSS2026.02 | 47.9 | |
| TableSQLifyCategory=Direct, Model=Gemini 2.02026.02 | 47.51 | |
| TableSQLifyCategory=Direct, Model=GPT-OSS2026.02 | 46.99 | |
| NormTabCategory=Direct, Model=Qwen 32026.02 | 46.8 | |
| CRAFTLLM Backbone=Llama-3.3-70B-Instruct, n=12025.05 | 46.21 | |
| CoT + SQLCategory=Direct, Model=Gemini 2.02026.02 | 43.29 | |
| RAGn=52025.05 | 39.67 | |
| CoT + SQLCategory=Direct, Model=Gemini 2.52026.02 | 36.64 | |
| TableSQLifyCategory=Direct, Model=Gemini 2.52026.02 | 34.78 | |
| CoT + SQLCategory=Direct, Model=Qwen 32026.02 | 34.54 | |
| CoT + SQLCategory=Direct, Model=DeepSeek V3.12026.02 | 34.21 |