List your company

Long-context Understanding on LongBench MuSiQue

22.32F1 ScoreDoc2Atom
4.55689.168413.7818.3916Jun 10, 2026

Evaluation results

MethodLinks
Doc2AtomLLM Backbone=Qwen3-4B-Instruct, Evaluation Protocol=Zero-shot2026.0622.3222.27
Base+ctxLLM Backbone=Gemma-2-2B-It, Evaluation Protocol=Zero-shot2026.0621.6221.62
Doc2AtomLLM Backbone=Gemma-2-2B-It, Evaluation Protocol=Zero-shot2026.0620.8620.86
Base+ctxLLM Backbone=Qwen3-4B-Instruct, Evaluation Protocol=Zero-shot2026.0618.1418.05
D2LrawLLM Backbone=Qwen3-4B-Instruct, Evaluation Protocol=Zero-shot2026.0612.2512.25
D2LckptLLM Backbone=Gemma-2-2B-It, Evaluation Protocol=Zero-shot2026.069.149.14
D2LatomLLM Backbone=Gemma-2-2B-It, Evaluation Protocol=Zero-shot2026.067.397.39
D2LrawLLM Backbone=Gemma-2-2B-It, Evaluation Protocol=Zero-shot2026.066.956.95
D2LatomLLM Backbone=Qwen3-4B-Instruct, Evaluation Protocol=Zero-shot2026.066.416.41
D2LckptLLM Backbone=Qwen3-4B-Instruct, Evaluation Protocol=Zero-shot2026.065.245