List your company

Reward Model Evaluation on Text-Expert (test fraction 0.2)

80.6Pair AccuracyArena BT
60.42465.66270.976.138Jun 24, 2026

Evaluation results

MethodLinks
Arena BTReward Model=proprietary RM2026.0680.60.69510.874
Arena Avg RewardReward Model=proprietary RM2026.0680.60.69510.874
DUALEVALReward Model=proprietary RM2026.06780.8930.940.833
Arena BTReward Model=Skywork-Reward-V2-Qwen3-8B2026.0677.90.220.350.247
Arena Avg RewardReward Model=Skywork-Reward-V2-Qwen3-8B2026.0677.70.2280.3540.222
Static 2PL2026.0670.110.6950.701
DUALEVALReward Model=Skywork-Reward-V2-Qwen3-8B2026.0661.20.9630.7240.657