Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Table Question Answering on ReachQA (test)
Loading...
74.85
Relaxed Accuracy
Human
38.97
48.285
57.6
66.915
Sep 9, 2025
Relaxed Accuracy
Updated 3mo ago
Evaluation Results
Method
Method
Links
Relaxed Accuracy
Human
Model Category=Baselin...
2025.09
74.85
Claude 3.5 Sonnet
Model Category=Proprie...
2025.09
63
Gemini 2.5 Pro
Model Category=Proprie...
2025.09
61.87
Qwen2.5-VL-7B-Instruct + Visual-TableQA
Model Category=Finetun...
2025.09
60.95
Gemini 2.5 Flash
Model Category=Proprie...
2025.09
56.97
Qwen2.5-VL-7B-Instruct + ReachQA
Model Category=Finetun...
2025.09
55.75
GPT-4o
Model Category=Proprie...
2025.09
53.25
Qwen2.5-VL-32B-Instruct
Model Category=Open-So...
2025.09
49.5
Qwen2.5-VL-7B-Instruct
Model Category=Open-So...
2025.09
49.23
Llama 4 Maverick 17B-128E Instruct
Model Category=Open-So...
2025.09
47.98
Mistral Small 3.1 24B Instruct
Model Category=Open-So...
2025.09
42.45
GPT-4o mini
Model Category=Proprie...
2025.09
40.35
Feedback
Search any
task
Search any
task