Our new X account is live! Follow @wizwand_team for updates

Reward Modeling on VLRewardBench (test)

84.7General

IXC-2.5-Reward

Updated 4d ago

Evaluation Results

Method	Links
IXC-2.5-Reward 2025.01		84.7	62.5	62.9	65.8	70
UnifiedReward-7B 2025.12		60.6	78.4	60.5	66.1	-
ARM-Thinker-7B 2025.12		55.7	72	64.8	67.8	-
LLaVA-Critic-8B 2025.01		54.6	38.3	59.1	41.2	44
Gemini-1.5-Pro (2024-09-24) 2025.01		50.8	72.5	64.2	67.2	62.5
GPT-4o (2024-08-06) 2025.01		49.1	67.6	70.5	65.8	62.4
GPT-4o 2025.12		49.1	67.6	70.5	65.8	-
InternVL3-8B 2025.12		48.1	51.3	48.1	50	-
Gemini-1.5-Flash (2024-09-24) 2025.01		47.8	59.6	58.4	57.6	55.3
InternVL3.5-8B 2025.12		47.5	51.3	51.9	50.9	-
Qwen3-VL-8B 2025.12		47	71.3	64.5	66	-
Claude-3.5-Sonnet (2024-06-22) 2025.01		43.4	55	62.3	55.3	53.6
Llama-3.2-90B 2025.01		42.6	57.3	61.7	56.2	53.9
GPT-4o-mini (2024-07-18) 2025.01		41.7	34.5	58.2	41.5	44.8
NVLM-D-72B 2025.01		38.9	31.6	62	40.1	44.1
Qwen2-VL-72B 2025.01		38.1	32.8	58	39.5	43
Qwen2.5-VL-7B 2025.12		37.7	48.7	60.4	50.1	-
InternVL2-8B 2025.01		35.6	41.1	59	44.5	45.2
Pixtral-12B 2025.01		35.6	25.9	59.9	35.8	40.4
Molmo-72B 2025.01		33.9	42.3	54.9	44.1	43.7
Llama-3.2-11B 2025.01		33.3	38.4	56.6	42.9	42.8
LLaVA-OneVision-7B-ov 2025.01		32.2	20.1	57.1	29.6	36.5
Qwen2-VL-7B 2025.01		31.6	19.1	51.1	28.3	33.9
Molmo-7B 2025.01		31.1	31.8	56.2	37.5	39.7