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

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

77.5PR

Claude-4-Sonnet

Updated 3d ago

Evaluation Results

Method	Links
Claude-4-Sonnet 2025.12		77.5	71.8
GPT-OSS 2025.12		68	73.5
Qwen3-Coder 2025.12		67	64
GPT-OSS 2025.12		64.3	68.5
Qwen3 2025.12		62.9	57.8
DeepSeek-R1 2025.12		60	53.5
Gemini-2.5-Pro 2025.12		57.2	56.8
Qwen3-VL 2025.12		54.6	50
Qwen3 2025.12		54.3	45.8
Qwen3-Coder 2025.12		54.1	49.8
Ovis2.5 2025.12		51.5	49.3
GPT-4o 2025.12		51.4	50
Gemma3 2025.12		47.1	43.5
Qwen2.5-VL 2025.12		44.5	38
Qwen2.5-VL 2025.12		43	33.8
Llama-3.3 2025.12		38.4	35.8
Gemma3 2025.12		36.7	37.2
GLM-4.1V-Thinking 2025.12		36.6	32.3
Qwen2.5-VL 2025.12		24.5	19.5
GLM-4.5V 2025.12		24.4	23.5