List your company

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

77.5PRClaude-4-Sonnet
22.27636.61350.9565.287Dec 5, 2025

Evaluation results

MethodLinks
Claude-4-SonnetNumber of Parameters=-, Feedback Type=Textual2025.1277.571.8
GPT-OSSNumber of Parameters=120B, Feedback Type=Textual2025.126873.5
Qwen3-CoderNumber of Parameters=480B, Feedback Type=Textual2025.126764
GPT-OSSNumber of Parameters=20B, Feedback Type=Textual2025.1264.368.5
Qwen3Number of Parameters=235B, Feedback Type=Textual2025.1262.957.8
DeepSeek-R1Number of Parameters=685B, Feedback Type=Textual2025.126053.5
Gemini-2.5-ProNumber of Parameters=-, Feedback Type=Textual2025.1257.256.8
Qwen3-VLNumber of Parameters=30B, Feedback Type=Textual2025.1254.650
Qwen3Number of Parameters=8B, Feedback Type=Textual2025.1254.345.8
Qwen3-CoderNumber of Parameters=30B, Feedback Type=Textual2025.1254.149.8
Ovis2.5Number of Parameters=9B, Feedback Type=Textual2025.1251.549.3
GPT-4oNumber of Parameters=-, Feedback Type=Textual2025.1251.450
Gemma3Number of Parameters=12B, Feedback Type=Textual2025.1247.143.5
Qwen2.5-VLNumber of Parameters=32B, Feedback Type=Textual2025.1244.538
Qwen2.5-VLNumber of Parameters=72B, Feedback Type=Textual2025.124333.8
Llama-3.3Number of Parameters=70B, Feedback Type=Textual2025.1238.435.8
Gemma3Number of Parameters=27B, Feedback Type=Textual2025.1236.737.2
GLM-4.1V-ThinkingNumber of Parameters=9B, Feedback Type=Textual2025.1236.632.3
Qwen2.5-VLNumber of Parameters=7B, Feedback Type=Textual2025.1224.519.5
GLM-4.5VNumber of Parameters=108B, Feedback Type=Textual2025.1224.423.5