ResearchBenchmarksReward Modeling on ManiRewardBench FrankaFollow94.2Mean VOCTOPReward-3.76821.66647.172.534Feb 22, 2026Evaluation ResultsMethodMethodLinksMean VOCTOPRewardBackbone=Qwen3-VL-8BBackbone=Qwen3-VL-8B2026.0294.2GVLBackbone=Gemini-2.5-Pr...Backbone=Gemini-2.5-Pro, Chat template enforced=true2026.0269.5TOPRewardBackbone=Molmo2-8BBackbone=Molmo2-8B2026.0266.2TOPRewardBackbone=Gemini-2.5-Pr...Backbone=Gemini-2.5-Pro, Chat template enforced=true2026.0244.8GVLBackbone=Qwen3-VL-8BBackbone=Qwen3-VL-8B2026.0224.2GVLBackbone=Molmo2-8BBackbone=Molmo2-8B2026.020