Share your thoughts, 1 month free Claude Pro on usSee more

Reward Model Evaluation on RewardBench 2

88.2Factuality

Scalar RM

Updated 2d ago

Evaluation Results

Method
Scalar RM 2026.05	88.2	67.8	83.1	97.3	99.2	83.1	86.4	-
LMUNITQwen2.5-72B 2024.12	87.2	54.4	72.7	91.3	96.8	90.1	82.1	-
LMUNITLLaMA3.1-70B 2024.12	84.6	48.8	71.6	90.7	97	90.6	80.5	-
Claude-opus-4 2024.12	84.2	47.9	73.6	73.8	93.8	91.7	77.5	-
Claude-opus-4 2024.12	82.7	41.9	74.9	89.5	86.2	83.7	76.5	-
LMUNITQwen2.5-72B 2024.12	82.5	45.6	69.4	90.9	93.3	86.7	78.1	-
gemini-2.5-flash 2024.12	82.2	57.5	77.7	56.2	78.4	82.2	72.4	-
allenai/Llama-3.1-70B-Instruct-RM-RB2 2024.12	81.3	41.9	69.9	88.4	86.5	88.3	76.1	-
QRM-Gemma-2-27B 2024.12	78.5	37.2	69.9	95.8	95.4	83.2	76.7	-
INF-ORM-Llama3.1-70B 2024.12	74.1	41.9	69.9	96.4	90.3	86.2	76.5	-
Skywork/Skywork-Reward-Gemma-2-27B 2024.12	73.7	40.3	70.5	94.2	93.2	82.6	75.8	-
Claude-3-7-sonnet 2024.12	73.3	54.4	75	90.3	92.1	67.2	75.4	-
LMUNITLLaMA3.1-70B 2024.12	71.6	36.3	71	92.9	91.3	88	75.2	-
gemini-2.5-flash-preview-04-17 2024.12	65.7	55.3	81.1	90.9	86.7	83.4	77.2	-
RUBRIC-ARM 2026.05	48.8	39.1	63.5	60.8	66.1	58.2	56.1	-
EVOLM 2026.05	37.2	30.6	54	43.5	54.4	56.1	46	-
Sequential 2026.05	37	32	57.1	42.3	59	55.6	47.2	-
RLCER 2026.05	33.1	29.8	52.2	48.3	51.9	54.8	45	-
GPT-4.1 2026.05	32.1	32.6	34.4	39.1	35	46.3	36.6	-
Sequential 2026.05	31.5	30.8	57	47.9	49.6	59.2	46	-
Qwen3-8B 2026.05	27.8	26.5	38.1	25	30.2	9.7	26.2	-
Skywork-Reward-V2-Llama-3.2-3B 2026.05	-	-	-	-	-	-	-	74.7
Continual Offline Training RM 2026.05	-	-	-	-	-	-	-	75.3
HL-BT 2026.05	-	-	-	-	-	-	-	74.9
Mean Reward 2026.05	-	-	-	-	-	-	-	65
SAVE 2026.05	-	-	-	-	-	-	-	76
SAVE (w/o Curriculum Mechanism) 2026.05	-	-	-	-	-	-	-	75.9
SAVE (w/o Policy Model Optimization) 2026.05	-	-	-	-	-	-	-	75.7
HL-BT 2026.05	-	-	-	-	-	-	-	75.1
Mean Reward 2026.05	-	-	-	-	-	-	-	65
SAVE 2026.05	-	-	-	-	-	-	-	76.1
SAVE (w/o Curriculum Mechanism) 2026.05	-	-	-	-	-	-	-	76.1
SAVE (w/o Policy Model Optimization) 2026.05	-	-	-	-	-	-	-	76