DDR_Bench / benchmarking_data.js
thinkwee
update benchmarking
845705b
// Benchmarking data for DDR-Bench
const benchmarkingData = {
proprietary: [
{ model: "Claude 4.5 Sonnet", acc: 47.73, logo: "logos/Anthropic.png" },
{ model: "GPT-5.2", acc: 37.09, logo: "logos/OpenAI.png" },
{ model: "GPT-5.1", acc: 36.27, logo: "logos/OpenAI.png" },
{ model: "GPT-5 mini", acc: 34.61, logo: "logos/OpenAI.png" },
{ model: "Gemini 3 Flash", acc: 30.65, logo: "logos/Google.png" },
{ model: "Gemini 2.5 Pro", acc: 25.00, logo: "logos/Google.png" },
{ model: "Gemini 2.5 Flash", acc: 20.17, logo: "logos/Google.png" },
{ model: "Gemini 2.5 Flash-Lite", acc: 18.94, logo: "logos/Google.png" }
],
opensource: [
{ model: "DeepSeek-V3.2", acc: 38.80, logo: "logos/DeepSeek.png" },
{ model: "GLM-4.6", acc: 37.52, logo: "logos/Zhipu.png" },
{ model: "Kimi K2", acc: 36.42, logo: "logos/Kimi.png" },
{ model: "MiniMax-M2", acc: 32.25, logo: "logos/minimax.png" },
{ model: "Qwen3-Next-80B-A3B", acc: 30.56, logo: "logos/Qwen.png" },
{ model: "Qwen3-30B-A3B", acc: 28.13, logo: "logos/Qwen.png" },
{ model: "Qwen3-4B", acc: 24.97, logo: "logos/Qwen.png" },
{ model: "Qwen2.5-72B", acc: 21.08, logo: "logos/Qwen.png" },
{ model: "Qwen2.5-14B-1M", acc: 19.23, logo: "logos/Qwen.png" },
{ model: "Qwen2.5-32B", acc: 19.06, logo: "logos/Qwen.png" },
{ model: "Qwen2.5-14B", acc: 18.49, logo: "logos/Qwen.png" },
{ model: "Qwen2.5-7B", acc: 14.81, logo: "logos/Qwen.png" },
{ model: "Qwen2.5-7B-1M", acc: 14.56, logo: "logos/Qwen.png" },
{ model: "Llama3.3-70B", acc: 12.30, logo: "logos/meta.png" }
]
};