List your company

Reward Modeling on OGRBench

88.1Ubuntu AccuracyQwen3-VL-235B
45.35656.45367.5578.647Mar 19, 2026

Evaluation results

MethodLinks
Qwen3-VL-235BFramework=OS-Themis2026.0388.188.392.392.877.568.494.886.792.192.28892.882.387.2
Gemini-3-FlashFramework=OS-Themis2026.038584.79191.186.983.793.582.882.680.586.293.27884.9
Qwen3-VL-235B-ThinkingFramework=OS-Themis2026.0383.483.789.489.685.582.593.582.884.783.485.289.379.984.3
GPT-5Framework=OS-Themis2026.0382.581.380.378.484.580.588.360.995.980.482.993.470.680.4
Qwen3-VL-30B-A3BFramework=OS-Themis2026.0379.579.484.68576.570.988.366.780.579.380.384.773.778.8
Qwen3-VL-32BFramework=OS-Themis2026.0377.675.283.582.175.163.588.36984.783.379.692.264.375.8
Qwen3-VL-8BFramework=OS-Themis2026.0377.275.885.685.172.861.885.759.386.387.279.386.369.477
Qwen3-VL-235BFramework=ZeroGUI2026.0376.574.582.584.277.970.893.581.584.785.679.685.570.977.5
Gemini-3-FlashFramework=ZeroGUI2026.0376.172.877.17680.874.593.581.577.475.178.189.86374.1
Qwen3-VL-32BFramework=ZeroGUI2026.037572.278.78079.372.589.666.776.375.977.285.365.374
Qwen3-VL-30B-A3BFramework=ZeroGUI2026.0374.874.680.382.880.877.390.975.972.175.176.977.974.976.3
Qwen3-VL-8BFramework=ZeroGUI2026.0372.767.878.779.676.567.589.669.275.87575.486.360.170.9
GPT-5Framework=ZeroGUI2026.0372.66781.982.377.568.890.97280.579.676.789.759.971.8
Qwen3-VL-235B-ThinkingFramework=ZeroGUI2026.0371.866.979.882.179.372.589.666.77978.375.985.362.372
Gemini-3-FlashFramework=DigiRL2026.0369.56369.764.276.566.283.131.675.374.372.186.651.964.9
GPT-5-miniFramework=OS-Themis2026.0368.859.765.452.576.564.38754.575.870.571.595.444.760.9
Qwen3-VL-32BFramework=DigiRL2026.0365.766.572.377.871.871.275.355.862.167.967.665.872.168.8
Qwen3-VL-235BFramework=DigiRL2026.0365.56770.275.272.370.976.643.863.262.867.466.66967.8
Qwen3-VL-235B-ThinkingFramework=DigiRL2026.0362.466.367.574.765.76670.146.558.462.263.5617366.5
Qwen3-VL-8BFramework=DigiRL2026.0362.164.969.276.666.263.672.74063.269.664.462.272.166.8
Qwen3-VL-30B-A3BFramework=DigiRL2026.036167.66775.66971.167.54954.26362.558.980.668.1
GPT-5Framework=DigiRL2026.0350.513.756.933.159.117.179.2052.616.754.589.39.617.3
GPT-5-miniFramework=ZeroGUI2026.0348.56.449.55.956.32.179.20495.851.5872.95.5
GPT-5-miniFramework=DigiRL2026.0347047.9055.9079.2047.9050.3000