List your company

Weather Report Generation on WeatherTGD Dataset

8.68LLM SA ScoreWeatherTGD
5.28966.16987.057.9302Mar 23, 2026

Evaluation results

MethodLinks
WeatherTGDLLM Backbone=Qwen3-Next, Tok.=3.52026.038.688.568.828.698.528.428.688.5448.254.285.8
WeatherTGDLLM Backbone=MiniMax-01, Tok.=3.52026.038.528.388.688.538.368.228.528.3746.852.884.5
WeatherTGDLLM Backbone=Average, Tok.=3.52026.038.488.378.648.58.328.228.498.3446.752.784.5
WeatherTGDLLM Backbone=DeepSeek-V3, Tok.=3.52026.038.248.188.428.288.088.028.268.1245.251.283.2
AVerseLLM Backbone=Qwen3-Next, Tok.=3.82026.037.457.127.327.37.326.987.187.1441.848.581.5
DebateLLM Backbone=Qwen3-Next, Tok.=4.52026.037.387.227.127.247.247.086.987.1241.247.880.8
MADLLM Backbone=Qwen3-Next, Tok.=4.22026.037.287.147.047.157.167.026.97.0240.547.280.5
CAMELLLM Backbone=Qwen3-Next, Tok.=3.22026.037.247.026.927.067.16.886.766.939.846.279.8
AVerseLLM Backbone=MiniMax-01, Tok.=3.82026.037.186.827.027.017.046.686.886.8639.846.280.2
AVerseLLM Backbone=Average, Tok.=3.82026.037.186.837.027.017.046.686.886.8639.946.580.2
DebateLLM Backbone=MiniMax-01, Tok.=4.52026.037.126.946.826.966.986.86.686.839.545.879.5
DebateLLM Backbone=Average, Tok.=4.52026.037.126.956.836.976.976.86.696.8239.545.979.5
AutoGenLLM Backbone=Qwen3-Next, Tok.=2.82026.037.086.826.966.956.926.666.86.7838.844.878.8
MADLLM Backbone=MiniMax-01, Tok.=4.22026.037.046.886.746.896.96.746.586.7438.845.279.2
MADLLM Backbone=Average, Tok.=4.22026.037.036.886.756.896.896.756.616.7538.845.379.2
SCLLM Backbone=Qwen3-Next, Tok.=5.02026.037.026.767.086.956.886.626.946.7838.244.278.2
CAMELLLM Backbone=MiniMax-01, Tok.=3.22026.036.986.726.646.786.826.566.486.6238.244.578.6
CAMELLLM Backbone=Average, Tok.=3.22026.036.986.736.656.796.826.576.496.6238.244.578.6
AVerseLLM Backbone=DeepSeek-V3, Tok.=3.82026.036.926.546.726.736.766.386.586.5738.244.878.8
DebateLLM Backbone=DeepSeek-V3, Tok.=4.52026.036.856.686.566.76.686.526.426.5537.844.278.2
AutoGenLLM Backbone=MiniMax-01, Tok.=2.82026.036.826.546.686.686.666.386.526.537.243.277.8
AutoGenLLM Backbone=Average, Tok.=2.82026.036.816.556.696.686.656.396.536.5137.343.477.8
MADLLM Backbone=DeepSeek-V3, Tok.=4.22026.036.786.626.486.636.626.486.346.4837.243.577.8
SCLLM Backbone=Average, Tok.=5.02026.036.756.496.86.686.596.356.656.5236.742.877.2
SCLLM Backbone=MiniMax-01, Tok.=5.02026.036.746.486.786.676.586.346.626.5236.842.877.2
CAMELLLM Backbone=DeepSeek-V3, Tok.=3.22026.036.726.456.386.526.546.286.226.3536.542.877.4
AutoGenLLM Backbone=DeepSeek-V3, Tok.=2.82026.036.546.286.426.416.386.126.266.2435.842.176.8
SCLLM Backbone=DeepSeek-V3, Tok.=5.02026.036.486.226.546.416.326.086.386.2635.241.576.2
VanillaLLM Backbone=Qwen3-Next, Tok.=1.02026.035.855.625.745.745.75.485.625.634.240.875.8
VanillaLLM Backbone=MiniMax-01, Tok.=1.02026.035.685.425.585.565.525.285.445.4232.839.875.2
VanillaLLM Backbone=Average, Tok.=1.02026.035.655.415.565.545.55.275.435.432.739.775.1
VanillaLLM Backbone=DeepSeek-V3, Tok.=1.02026.035.425.185.365.325.285.045.225.1831.238.574.2