List your company
ResearchFormerly WizWand

Visualization Generation on MatPlotAgent

72.23Quality ScoreClaude-4-Sonnet
-2.42182416.95893836.339755.720462Oct 25, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Claude-4-SonnetFeedback Model=VISJUDGE as Feedback2025.1072.23
Gemini-2.5-ProFeedback Model=VISJUDGE as Feedback2025.1072.2
GPT-5Feedback Model=VISJUDGE as Feedback2025.1072.07
GPT-4oFeedback Model=VISJUDGE as Feedback2025.1071.62
GPT-5Feedback Model=Qwen2.5-VL-72B as Feedback2025.1069.8
Claude-3.5-SonnetFeedback Model=VISJUDGE as Feedback2025.1069.04
Gemini-2.5-ProFeedback Model=Direct Decoding (Baseline)2025.1068.1
Qwen2.5-VL-72B-InstructFeedback Model=VISJUDGE as Feedback2025.1067.32
Claude-4-SonnetFeedback Model=Qwen2.5-VL-7B as Feedback2025.1067.25
GPT-5Feedback Model=Direct Decoding (Baseline)2025.1067.15
GPT-5Feedback Model=Qwen2.5-VL-7B as Feedback2025.1066.49
Gemini-2.5-ProFeedback Model=Qwen2.5-VL-72B as Feedback2025.1066.12
Claude-4-SonnetFeedback Model=Qwen2.5-VL-72B as Feedback2025.1065.2
Gemini-2.5-ProFeedback Model=Qwen2.5-VL-7B as Feedback2025.1065.04
Claude-4-SonnetFeedback Model=Direct Decoding (Baseline)2025.1064.5
Claude-3.5-SonnetFeedback Model=Direct Decoding (Baseline)2025.1063.89
GPT-4oFeedback Model=Qwen2.5-VL-72B as Feedback2025.1063.53
Claude-3.5-SonnetFeedback Model=Qwen2.5-VL-72B as Feedback2025.1063.14
GPT-4oFeedback Model=Direct Decoding (Baseline)2025.1062.71
Qwen2.5-VL-72B-InstructFeedback Model=Direct Decoding (Baseline)2025.1061.18
Qwen2.5-VL-72B-InstructFeedback Model=Qwen2.5-VL-72B as Feedback2025.1060.3
Claude-3.5-SonnetFeedback Model=Qwen2.5-VL-7B as Feedback2025.1059.23
Qwen2.5-VL-72B-InstructFeedback Model=Qwen2.5-VL-7B as Feedback2025.1058.7
GPT-4oFeedback Model=Qwen2.5-VL-7B as Feedback2025.1058.49
Qwen2.5-VL-7B-InstructFeedback Model=VISJUDGE as Feedback2025.1055.29
Qwen2.5-VL-7B-InstructFeedback Model=Direct Decoding (Baseline)2025.1049.76
Qwen2.5-VL-7B-InstructFeedback Model=Qwen2.5-VL-7B as Feedback2025.1045.38
Qwen2.5-VL-7B-InstructFeedback Model=Qwen2.5-VL-72B as Feedback2025.1044.94
Claude-4-SonnetFeedback Model=VISJUDGE2025.100.7223
Gemini-2.5-ProFeedback Model=VISJUDGE2025.100.722
GPT-5Feedback Model=VISJUDGE2025.100.7207
GPT-4oFeedback Model=VISJUDGE2025.100.7162
GPT-5Feedback Model=Qwen2.5-VL-72B2025.100.698
Claude-3.5-SonnetFeedback Model=VISJUDGE2025.100.6904
Gemini-2.5-ProFeedback Model=Direct Decoding (Baseline)2025.100.681
Qwen2.5-VL-72B-InstructFeedback Model=VISJUDGE2025.100.6732
Claude-4-SonnetFeedback Model=Qwen2.5-VL-7B2025.100.6725
GPT-5Feedback Model=Direct Decoding (Baseline)2025.100.6715
GPT-5Feedback Model=Qwen2.5-VL-7B2025.100.6649
Gemini-2.5-ProFeedback Model=Qwen2.5-VL-72B2025.100.6612
Claude-4-SonnetFeedback Model=Qwen2.5-VL-72B2025.100.652
Gemini-2.5-ProFeedback Model=Qwen2.5-VL-7B2025.100.6504
Claude-4-SonnetFeedback Model=Direct Decoding (Baseline)2025.100.645
Claude-3.5-SonnetFeedback Model=Direct Decoding (Baseline)2025.100.6389
GPT-4oFeedback Model=Qwen2.5-VL-72B2025.100.6353
Claude-3.5-SonnetFeedback Model=Qwen2.5-VL-72B2025.100.6314
GPT-4oFeedback Model=Direct Decoding (Baseline)2025.100.6271
Qwen2.5-VL-72B-InstructFeedback Model=Direct Decoding (Baseline)2025.100.6118
Qwen2.5-VL-72B-InstructFeedback Model=Qwen2.5-VL-72B2025.100.603
Claude-3.5-SonnetFeedback Model=Qwen2.5-VL-7B2025.100.5923
Qwen2.5-VL-72B-InstructFeedback Model=Qwen2.5-VL-7B2025.100.587
GPT-4oFeedback Model=Qwen2.5-VL-7B2025.100.5849
Qwen2.5-VL-7B-InstructFeedback Model=VISJUDGE2025.100.5529
Qwen2.5-VL-7B-InstructFeedback Model=Direct Decoding (Baseline)2025.100.4976
Qwen2.5-VL-7B-InstructFeedback Model=Qwen2.5-VL-7B2025.100.4538
Qwen2.5-VL-7B-InstructFeedback Model=Qwen2.5-VL-72B2025.100.4494