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

Visual Instruction Following on FronTalk Multi-Turn 1.0 (test)

75PR Score

Gemini-2.5-Pro

Updated 3d ago

Evaluation Results

Method	Links
Gemini-2.5-Pro 2025.12		75	4.5	71
Gemini-2.5-Pro 2025.12		68.7	6.2	73.8
Qwen3-Coder 2025.12		62.5	15.4	62.3
GPT-OSS 2025.12		61.6	15.8	71.5
Qwen3-Coder 2025.12		61	8.6	54.3
Qwen3 2025.12		59.9	13.9	57.8
Claude-4-Sonnet 2025.12		59.3	10.6	64.8
Qwen3 2025.12		59	20.6	61.3
GPT-OSS 2025.12		57.9	9.2	66.8
GPT-4o 2025.12		56	21.4	55
GPT-4o 2025.12		55	8	52.5
Qwen3-VL 2025.12		54.1	4.7	50.3
Qwen2.5-VL 2025.12		52.8	17.8	46.5
Claude-4-Sonnet 2025.12		45.5	22.8	60.8
Qwen2.5-VL 2025.12		44.6	15.4	37.3
Gemma3 2025.12		43.8	30.3	43
Qwen3-VL 2025.12		39.1	12.3	35.8
Gemma3 2025.12		37.2	42.1	39.5
Qwen2.5-VL 2025.12		36.9	25.7	36.5
Gemma3 2025.12		35.5	16.7	41
Ovis2.5 2025.12		35.3	12.2	34.3
GLM-4.5V 2025.12		35.2	9.8	40.5
Qwen2.5-VL 2025.12		33.2	46.9	37.5
Gemma3 2025.12		30.4	22.1	38.5
Llama-3.3 2025.12		28.9	46.3	40.8
Ovis2.5 2025.12		27	10.5	39.5
DeepSeek-R1 2025.12		24.7	34.5	40
Qwen2.5-VL 2025.12		23.7	28.2	26.8
GLM-4.1V-Thinking 2025.12		18.2	5.8	41.5
Qwen2.5-VL 2025.12		16.1	39.3	17
GLM-4.1V-Thinking 2025.12		15.3	4.3	32
GLM-4.5V 2025.12		7.9	27.7	7.8