Our new X account is live! Follow @wizwand_team for updates

Data Analysis on RealHitBench

79.55GPT Score

DeepSeek-R1

Updated 4d ago

Evaluation Results

Method
DeepSeek-R1 2025.06	79.55	42.59
GPT4o(TreeThinker) 2025.06	79.45	37.08
GPT4o(TreeThinker) 2025.06	77.26	37.63
Doubao-1.5-pro-32k 2025.06	75.21	36.01
Gemini1.5-pro 2025.06	74.8	36.26
GPT4o 2025.06	73.37	36.36
GPT4o 2025.06	72.05	35.25
GPT4o(TreeThinker) 2025.06	70.83	34.44
Gemini1.5-pro 2025.06	70.72	36.17
QwQ-32B 2025.06	68.66	20.86
Qwen2.5-72B-Instruct 2025.06	68.45	35.9
Gemini1.5-pro 2025.06	67.22	36.26
Qwen3-32B 2025.12	66.67	-
TableGPT-R1-8B 2025.12	66.53	-
DeepSeek-V3 2025.12	66.29	-
GPT4o 2025.06	65.24	33.1
QwQ-32B 2025.12	64.99	-
Qwen3-14B 2025.12	63.03	-
TableGPT2-7B 2025.06	62.76	33.25
Qwen-Plus 2025.12	62.04	-
Llama-3.1-8B 2025.12	60.12	-
Llama3.1-8B-Instruct 2025.06	60.12	32.25
Mistral-7B-Instruct-v0.3 2025.06	57.74	19.84
Llama3.2-90B-Vision-Instruct 2025.06	57.28	31.87
GPT-4o 2025.12	55.54	-
DeepSeek-R1-Distill-Llama-8B 2025.06	54.55	26.98
DeepSeek-R1-Distill-Qwen-7B 2025.06	54.39	25.19
Qwen3-8B 2025.12	53.28	-
Qwen3-72B 2025.12	53.27	-
TableGPT2-7B 2025.12	53.16	-
Llama3.2-90B-Vision-Instruct 2025.06	53.06	32.36
Llama3.2-11B-Vision-Instruct 2025.06	52.75	30.59
Llama3.3-70B-Instruct 2025.06	52.26	27.98
TableLLM 2025.12	47.86	-
TableLLM-Llama3.1-8B 2025.06	47.86	27.26
TableLLM-Qwen2-7B 2025.06	47.3	18.86
Llama3.2-11B-Vision-Instruct 2025.06	41.32	22.75
Llama3.2-90B-Vision-Instruct 2025.06	41.18	25.46
Qwen2.5-7B-Instruct 2025.06	40.17	24.17
Llama3.2-11B-Vision-Instruct 2025.06	39.98	22.43
Qwen2-VL-7B-Instruct 2025.06	39.69	25.39
DeepSeek-R1-Distill-Qwen-1.5B 2025.06	38.02	16.24
Qwen2-VL-7B-Instruct 2025.06	37.41	24.3
Table-R1-Zero-7B 2025.12	36.24	-
mPLUG-Owl3-7B 2025.06	30.71	18.53
LLaVa-v1.5-7B 2025.06	26.6	17.74
mPLUG-Owl2-7B 2025.06	25.46	12.13
TableLlama 2025.06	24.73	7.89
Table-LLava-7B 2025.06	22.46	8.72