List your company

Multimodal Preference Evaluation on MMRB2

80.2T2I AccuracyMJ1
49.20857.25465.373.346Mar 9, 2026

Evaluation results

MethodLinks
MJ1Model Family/Base Model=Qwen3-VL-30B-A3B, Fine-tuning Protocol (e.g., LoRA)=LoRA, Active Parameters=3B2026.0380.278.173.576.477
Gemini 3 ProModel Category (Open-source vs API-based)=API-based2026.0374.474.976.479.576.3
GPT-5Model Category (Open-source vs API-based)=API-based2026.0370.573.874.470.272.2
Gemini 2.5 ProModel Category (Open-source vs API-based)=API-based2026.0370.571.375.166.670.9
GPT-4.1Model Category (Open-source vs API-based)=API-based2026.0365.868.2675363.5
Qwen3-VL-32BModel Category (Open-source vs API-based)=Open-source, Active Parameters=32B2026.0364.167.370.556.664.6
Gemini 2.5 FlashModel Category (Open-source vs API-based)=API-based2026.0363.166.569.457.564.1
Qwen3-VL-235B-A22BModel Category (Open-source vs API-based)=Open-source, Active Parameters=22B2026.036264.86955.962.9
GPT-4oModel Category (Open-source vs API-based)=API-based2026.0360.36561.551.959.7
Qwen3-VL-30B-A3BModel Category (Open-source vs API-based)=Open-source, Active Parameters=3B2026.036059.557.357.358.5
Qwen3-VL-8BModel Category (Open-source vs API-based)=Open-source, Active Parameters=8B2026.0359.461.761.554.659.3
Qwen2.5-VL-72BModel Category (Open-source vs API-based)=Open-source, Active Parameters=72B2026.0359.164.662.35059
Gemma 3 27BModel Category (Open-source vs API-based)=Open-source, Active Parameters=27B2026.0358.360.261.149.457.3
Gemma 3 12BModel Category (Open-source vs API-based)=Open-source, Active Parameters=12B2026.0356585849.355.3
Gemma 3 4BModel Category (Open-source vs API-based)=Open-source, Active Parameters=4B2026.0351.75151.348.850.7
Qwen2.5-VL-7BModel Category (Open-source vs API-based)=Open-source, Active Parameters=7B2026.0350.457.148.447.550.9