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

Reward Modeling on RM-Bench (test)

84.11Chat Score

Eval-Skill (workflow-only)

Updated 1mo ago

Evaluation Results

Method
Eval-Skill (workflow-only) 2026.06	84.11	96.17	87.5	94.69	-	90.62	-	-	-
Eval-Skill (full) 2026.06	82.28	96.37	85.59	95.73	-	89.99	-	-	-
Eval-Skill (adaptive) 2026.06	82.28	96.37	85.59	95.73	-	89.99	-	-	-
Principles-Qwen32B 2026.02	80.4	92	77	95.5	86.2	83.8	-	-	-
Direct 2026.06	77.78	89.74	80.9	94.17	-	85.65	-	-	-
Eval-Skill (workflow-only) 2026.06	77.64	94.82	75.17	91.53	-	84.79	-	-	-
Eval-Skill (full) 2026.06	77.22	94.95	76.22	91.82	-	85.05	-	-	-
Eval-Skill (adaptive) 2026.06	77.22	94.95	76.22	91.82	-	85.05	-	-	-
Eval-Skill (workflow-only) 2026.06	76.79	88.58	79.86	93.74	-	84.74	-	-	-
Eval-Skill (adaptive) 2026.06	76.79	90.65	79.86	94.2	-	85.38	-	-	-
DeepSeek-R1-0528 2026.02	76.7	74.3	51	89.2	72.8	75.8	-	-	-
RewardAnything-8B-v1 2026.02	76.7	90.3	75.2	90.2	83.1	72.9	-	-	-
GRAM-R² 2026.02	76	89.8	80.6	96.2	85.7	83.4	-	-	-
Qwen3-14B 2026.02	75.7	95.7	82.2	93.2	86.7	82.9	-	-	-
Eval-Skill (full) 2026.06	74.96	90.65	79.43	94.2	-	84.81	-	-	-
Qwen3-30B-A3B 2026.02	74.9	95.5	84.4	93.6	87.1	84.6	-	-	-
RM-R1-Distilled-Qwen-32B 2026.02	74.2	91.8	74.1	95.4	83.9	81.4	-	-	-
Scaled BT 2026.02	74.2	59.2	53.4	82.3	-	67.3	47.6	69.7	84.4
Nemotron-Super 2026.02	73.7	91.4	75	90.6	82.7	80	-	-	-
Qwen3-14B (Outcome-Only) 2026.02	72.3	92.6	77.8	91.7	83.6	76.8	-	-	-
Skywork-Reward-Gemma-2-27B 2026.02	71.8	59.2	56.6	94.3	70.5	67.8	-	-	-
RM-R1-Distilled-Qwen-14B 2026.02	71.8	90.5	69.5	94.1	81.5	79.8	-	-	-
Margin BT 2026.02	71.7	58.7	53.2	76.5	-	65	39	68.1	88
Soft Label 2026.02	70.8	57.8	53.6	86.2	-	67.1	42.1	69.8	89.4
Margin BT 2026.02	70	55.5	50.6	71.8	-	62	41.4	63.6	80.9
Skywork-Reward-Llama-3.1-8B 2026.02	69.5	60.6	54.5	95.7	70.1	66.3	-	-	-
NLL-Sym 2026.02	69.5	58.6	54.1	88.1	-	67.6	41.3	71.3	80.2
Scaled BT 2026.02	69.4	55.1	49.2	69.3	-	60.7	35.5	63.1	83.7
Scaled BT 2026.02	69.2	55.1	50.1	59.3	-	58.4	36.1	59.7	79.4
All-Thresh 2026.02	68.8	56.6	51.9	86	-	65.8	42.1	68.1	87.4
Qwen3-30B-A3B (Outcome-Only) 2026.02	68.7	95.9	81.3	93.6	84.9	80.3	-	-	-
NLL-Asym 2026.02	68.4	58.7	56.9	81.5	-	66.6	53.9	68.3	77.6
NLL-Sym 2026.02	68.4	54.8	50.2	72.7	-	61.5	35.7	64	84.7
GPT-4o 2026.02	67.2	67.5	63.6	91.7	72.5	66.2	-	-	-
Margin BT 2026.02	66.8	55.9	53.2	67.8	-	60.9	38.6	62.9	81.3
RRM-32B 2026.02	66.6	81.4	65.2	79.4	73.1	74.4	-	-	-
Direct 2026.06	66.53	70.71	59.38	90.03	-	71.66	-	-	-
All-Thresh 2026.02	66.3	57.3	54	81.5	-	64.8	52.6	66.3	75.5
Margin BT 2026.02	66.2	56.3	52.1	88.5	-	65.7	36.3	70.1	90.8
NLL-Sym 2026.02	66.1	53.3	51.9	83.5	-	63.7	39.9	66.7	84.6
NLL-Sym 2026.02	65.4	53.8	54	85.8	-	64.7	40.6	67.3	86.4
Soft Label 2026.02	65.3	56.4	52.5	60.5	-	58.7	31.8	61.8	82.5
Direct 2026.06	64.84	78.27	69.79	91.53	-	76.11	-	-	-
Soft Label 2026.02	64.3	55.6	49.4	63.8	-	58.3	47.4	58.9	68.6
NLL-Asym 2026.02	64.3	55.4	33.6	51.9	-	56.3	30.3	56.9	81.7
NLL-Sym 2026.02	63.8	55	50.8	90.7	-	65.1	48.7	66.8	79.8
NLL-Sym 2026.02	63.8	53.5	50.4	72.5	-	60.1	29.4	63.1	87.8
Scaled BT 2026.02	63.6	55.2	49.7	79.8	-	62.1	38.9	64	83.2
Soft Label 2026.02	63.5	53.1	50.4	84	-	62.7	34.9	65.8	87.5
Margin BT 2026.02	63.4	53.9	49.6	76	-	60.7	31.7	64.3	86.2
Eval-Skill (full) 2026.06	63.01	57.24	49.83	69.99	-	60.02	-	-	-
Eval-Skill (adaptive) 2026.06	63.01	59.44	47.57	69.99	-	60	-	-	-
All-Thresh 2026.02	62.8	53.4	49.8	79.6	-	61.4	32.9	63.8	87.5
All-Thresh 2026.02	62.8	55.2	52.1	51.3	-	55.3	29.7	57	79.4
Claude-3.5-Sonnet 2026.02	62.5	62.6	54.4	64.4	61	62.9	-	-	-
Eval-Skill (workflow-only) 2026.06	62.45	78.43	54.34	84.62	-	69.96	-	-	-
Direct 2026.06	62.31	75.24	53.73	80.06	-	67.84	-	-	-
NLL-Asym 2026.02	62.2	58	52.2	70.6	-	60.8	39.2	63.3	79.8
Scaled BT 2026.02	62.1	53.4	50.1	76.2	-	60.5	32.7	63.7	85
All-Thresh 2026.02	62.1	56	52.3	55.5	-	56.5	25.5	59.9	84.1
All-Thresh 2026.02	61.9	51.9	49.3	77.5	-	60.1	31.5	63	85.9
Margin BT 2026.02	61.5	51.9	51.1	85.6	-	62.5	39.2	64.2	84.1
Scaled BT 2026.02	61.3	54.8	52	83.7	-	63	43.9	65.4	79.5
NLL-Asym 2026.02	60.4	53	50.9	65	-	57.3	23	61.7	87.3
Eval-Skill (full) 2026.06	58.79	80.78	56.68	83.87	-	70.03	-	-	-
Eval-Skill (adaptive) 2026.06	58.79	80.78	56.68	83.87	-	70.03	-	-	-
NLL-Asym 2026.02	58.4	53.9	48.3	71.6	-	58	28	61.7	84.5
Eval-Skill (workflow-only) 2026.06	58.37	59.44	47.57	67.64	-	58.26	-	-	-
NLL-Asym 2026.02	57.4	54.4	52.3	82.3	-	61.6	39.7	63.1	81.9
Soft Label 2026.02	57.1	55	50.5	72.7	-	58.8	22.5	63.8	90.2
Direct 2026.06	52.74	59.52	50.43	38.09	-	50.2	-	-	-
Soft Label 2026.02	52.5	50.1	49.1	62.3	-	53.5	26.5	53.7	80.3
GPT-4o 2026.01	-	-	-	-	72.5	-	-	-	-
Llama-3.3-70B-Instruct 2026.01	-	-	-	-	69.5	-	-	-	-
JudgeLRM-7B 2026.01	-	-	-	-	58.7	-	-	-	-
RM-R1-Qwen-7B 2026.01	-	-	-	-	70.2	-	-	-	-
RM-R1-Qwen-32B 2026.01	-	-	-	-	79.1	-	-	-	-
RRM-7B 2026.01	-	-	-	-	70.8	-	-	-	-
RRM-32B 2026.01	-	-	-	-	82.8	-	-	-	-
RISE-Judge-7B 2026.01	-	-	-	-	68	-	-	-	-
RISE-Judge-32B 2026.01	-	-	-	-	72.3	-	-	-	-
Think-J-32B 2026.01	-	-	-	-	79.8	-	-	-	-
CompassJudger2-7B 2026.01	-	-	-	-	71.5	-	-	-	-
CompassJudger2-32B 2026.01	-	-	-	-	73.2	-	-	-	-
J1-Llama-8B 2026.01	-	-	-	-	73.4	-	-	-	-
J1-Llama-70B 2026.01	-	-	-	-	82.7	-	-	-	-
Gemini-2.5-Flash 2026.01	-	-	-	-	70.8	-	-	-	-
CompassJudger1-32B 2026.01	-	-	-	-	54.4	-	-	-	-
TIR-Judge-Distill-4B 2026.01	-	-	-	-	71.9	-	-	-	-
TIR-Judge-Zero-4B 2026.01	-	-	-	-	72.8	-	-	-	-
TIR-Judge-Distill-8B 2026.01	-	-	-	-	76.7	-	-	-	-
TIR-Judge-Zero-8B 2026.01	-	-	-	-	76.3	-	-	-	-
CE-RM-4B 2026.01	-	-	-	-	79.8	-	-	-	-
CE-RM-4B 2026.01	-	-	-	-	81.9	-	-	-	-
CE-RM-4B 2026.01	-	-	-	-	83.2	-	-	-	-
Llama-3-OffsetBias-RM-8B 2025.07	-	-	-	-	71.3	-	-	-	-
ArmoRM-Llama3-8B-v0.1 2025.07	-	-	-	-	69.2	-	-	-	-
Internlm2-20b-reward 2025.07	-	-	-	-	72.1	-	-	-	-
Skywork-Reward-Llama-3.1-8B-v0.2 2025.07	-	-	-	-	64.7	-	-	-	-
LDL-Reward-Gemma-2-27B-v0.1 2025.07	-	-	-	-	71	-	-	-	-

Showing 100 of 119 rows