List your company

Reward Modeling on RM-Bench (full)

83Chat ScoreCodeScaler
60.84866.59972.3578.101Jan 21, 2025Mar 25, 2025May 27, 2025Jul 29, 2025Sep 30, 2025Dec 2, 2025Feb 4, 2026

Evaluation results

MethodLinks
CodeScalerModel size=8B2026.028379.976.996.492.587.971.884.1
SkyworkRMModel size=8B2026.0280.67573.696.591.885.56781.4
AceCodeRMModel size=32B2026.0273.770.572.18878.378.365.576.1
Nemotron-4-340B-RewardType=Generative2025.0171.259.859.487.58171.456.169.5
URM-LLaMa-3.1-8BType=Seq.2025.0171.261.854.193.18473.25370
Skyword-Reward-Llama3.1-8BType=Seq.2025.0169.560.654.595.78974.746.670.1
AceCodeRMModel size=7B2026.0266.765.366.989.979.974.462.272.2
Tulu-2-dpo-13bType=Implicit2025.0166.451.451.885.486.966.737.763.8
IXC-2.5-RewardType=Seq.2025.0165.555.951.793.887.571.347.468.8
InternLM2-20B-RewardType=Seq.2025.0163.166.856.786.582.671.650.768.3
InternLM2-7B-RewardType=Seq.2025.0161.771.449.785.585.470.745.167.1