ResearchBenchmarksLong-context Question Answering on LongBench VI. Long Structured Data Understanding v2For AI assistantsMarkdownContent indexLong-context Question Answering on LongBench VI. Long Structured Data Understanding v2Follow66.7AccuracyRLM26.55636.97847.457.822Jul 1, 2026Evaluation resultsMethodMethodLinksAccuracyLatency (s)RLMBackbone=Qwen3.6-35B-A3BBackbone=Qwen3.6-35B-A3B2026.0766.7104.2MPLMBackbone=Qwen3-30B-A3BBackbone=Qwen3-30B-A3B2026.0742.464.2MPLMBackbone=Qwen3.6-35B-A3BBackbone=Qwen3.6-35B-A3B2026.0739.4103.5RLMBackbone=Qwen3-30B-A3BBackbone=Qwen3-30B-A3B2026.0728.199.8