Visual Question Answering on AnimalKB 1.0 (test) benchmark leaderboard · SOTA2 Research

Visual Question Answering on AnimalKB 1.0 (test)

98.68Visual Accgpt-4o (0806)

Evaluation Results

Method	Links
gpt-4o (0806)2025.12		98.68	97.79	98.24
gpt-4o (1120)2025.12		98.26	97.87	98.06
gemini-2.0-flash2025.12		98.16	97.65	97.9
claude-3.5-sonnet2025.12		97.43	96.72	97.07
gemini-1.5-pro2025.12		97.01	96.54	96.78
gpt-4o-mini2025.12		94.04	95.07	94.56
claude-3-haiku2025.12		92.06	92.21	92.13
InternVL2.5-26B2025.12		87.99	88.04	88.01
Qwen2-VL-7B2025.12		87.67	86.91	87.29
InternVL2.5-8B2025.12		87.23	86.47	86.85
Qwen2.5-VL-7B2025.12		87.06	85.42	86.24
DeepSeek-VL2-Small2025.12		85.39	84.73	85.06
gemini-2.0-flash2025.12		84.95	81.96	83.46
DeepSeek-VL22025.12		84.66	85.1	84.88
LLaVA-Next-Llama3-8B2025.12		83.41	84.19	83.8
LLaVA-OV-Qwen2-7B2025.12		83.28	81.81	82.55
claude-3.5-sonnet2025.12		81.05	77.82	79.44
LLaVA-v1.6-Vicuna-7B2025.12		80.71	80.86	80.78
gpt-4o (0806)2025.12		79.36	77.13	78.25
gpt-4o (1120)2025.12		78.95	76.81	77.88
gemini-1.5-pro2025.12		78.68	78.68	79.71
InternVL2.5-26B2025.12		76.52	72.55	74.53
Qwen2-VL-7B2025.12		74.56	72.84	73.7
Qwen2.5-VL-7B2025.12		74.44	71.25	72.84
DeepSeek-VL22025.12		73.75	75.69	74.72
LLaVA-OV-Qwen2-7B2025.12		71.94	65.27	68.6
InternVL2.5-8B2025.12		71.27	69.09	70.18
gpt-4o-mini2025.12		69.78	66.86	68.32
DeepSeek-VL2-Small2025.12		66.13	68.7	67.41
LLaVA-v1.6-Vicuna-7B2025.12		65.76	60.91	63.33
LLaVA-Next-Llama3-8B2025.12		65.47	63.75	64.61
claude-3-haiku2025.12		63.82	59.14	61.48