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

Reward Modeling on MR2Bench Video

50.7BoN Score

Molmo2-4B RM

Updated 4d ago

Evaluation Results

Method	Links
Molmo2-4B RM 2026.04		50.7	77.4	0.55
Qwen3-VL-32B 2026.04		49.9	77.8	0.592
InternVL3-78B 2026.04		49.5	76.7	0.553
IXC-2.5-Reward 2026.04		48.7	74	0.491
Qwen3-VL-4B 2026.04		47.9	75.8	0.538
Qwen3-VL-8B 2026.04		47.7	77.2	0.563
Qwen3-VL-4B RM 2026.04		47.5	73.8	0.482
Skywork-VL-Reward 2026.04		46.7	74.4	0.499
R1-Reward 2026.04		44.8	68.4	0.496
Qwen2.5-VL-7B 2026.04		44.4	73.6	0.504
Molmo2-4B 2026.04		43.2	71.9	0.485
Molmo2-8B 2026.04		42.6	70.8	0.476
InternVL3-8B 2026.04		40.4	71.6	0.466
LLaVA-Critic 2026.04		40.2	69	0.421
MM-RLHF-Reward 2026.04		36.6	67	0.352