# Long-context consolidation on LongBench short: 16k–32k tokens v2 Source: [Long-context consolidation on LongBench short: 16k–32k tokens v2]() Collection index: [llms.txt]() Data updated: 2026-05-11T08:09:16.488Z Evaluation of model performance on the LongBench v2 short context subset (16k-32k tokens) specifically for the Long-context consolidation task, measured by Accuracy. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Long-context consolidation | | Dataset (including any stated split) | LongBench short: 16k–32k tokens v2 | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | SCoL | 42.3 | Not recorded | 6a016297dbc836b87d823165 | | SCoL | 42.3 | Not recorded | 6a016297dbc836b87d823165 | | Batch TTT | 39.5 | Not recorded | 6a016297dbc836b87d823165 | | Batch TTT | 39.5 | Not recorded | 6a016297dbc836b87d823165 | | Summarization | 39.3 | Not recorded | 6a016297dbc836b87d823165 | | Summarization | 39.3 | Not recorded | 6a016297dbc836b87d823165 | | Full Context | 38 | Not recorded | 6a016297dbc836b87d823165 | | Full Context | 38 | Not recorded | 6a016297dbc836b87d823165 | | Sequential FT | 36.5 | Not recorded | 6a016297dbc836b87d823165 | | Sequential FT | 36.5 | Not recorded | 6a016297dbc836b87d823165 | | Base | 32.5 | Not recorded | 6a016297dbc836b87d823165 | | Base | 32.5 | Not recorded | 6a016297dbc836b87d823165 | ### SCoL Accuracy: 42.3. Result ID: 6a018e9747f34ce924e33fbb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SCoL Accuracy: 42.3. Result ID: 6a018e9747f34ce924e33fcc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Batch TTT Accuracy: 39.5. Result ID: 6a018e9747f34ce924e33fb9. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Batch TTT Accuracy: 39.5. Result ID: 6a018e9747f34ce924e33fca. [Reporting paper]() Recorded evaluation configuration: {"training":"Batch LoRA"}. This record does not assert independent reproduction. ### Summarization Accuracy: 39.3. Result ID: 6a018e9747f34ce924e33fb8. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Summarization Accuracy: 39.3. Result ID: 6a018e9747f34ce924e33fc9. [Reporting paper]() Recorded evaluation configuration: {"summarizer":"Kimi-K2.6"}. This record does not assert independent reproduction. ### Full Context Accuracy: 38. Result ID: 6a018e9747f34ce924e33fb7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Full Context Accuracy: 38. Result ID: 6a018e9747f34ce924e33fc8. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Sequential FT Accuracy: 36.5. Result ID: 6a018e9747f34ce924e33fba. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Sequential FT Accuracy: 36.5. Result ID: 6a018e9747f34ce924e33fcb. [Reporting paper]() Recorded evaluation configuration: {"training":"Sequential LoRA"}. This record does not assert independent reproduction. ### Base Accuracy: 32.5. Result ID: 6a018e9747f34ce924e33fb6. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Base Accuracy: 32.5. Result ID: 6a018e9747f34ce924e33fc7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.