# Corpus-level evidence aggregation on CorpusQA 128K-token Source: [Corpus-level evidence aggregation on CorpusQA 128K-token]() Collection index: [llms.txt]() Data updated: 2026-06-04T08:49:50.810Z Evaluation of model performance on the CorpusQA 128K-token dataset, focusing on corpus-level evidence aggregation capabilities, typically measured using LLM-as-judge 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 | Corpus-level evidence aggregation | | Dataset (including any stated split) | CorpusQA 128K-token | | Metric | LLM-as-Judge Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 4 of 4 | | 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 - [LLM-as-Judge Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | LLM-as-Judge Accuracy | Result date | Report paper | | --- | --- | --- | --- | | InfoMem | 19.453 | Not recorded | 6a210666c10484bac23eff3b | | Outcome-only GRPO | 16.413 | Not recorded | 6a210666c10484bac23eff3b | | Qwen2.5-1.5B-Instruct | 14.59 | Not recorded | 6a210666c10484bac23eff3b | | ReMemR1 | 1.52 | Not recorded | 6a210666c10484bac23eff3b | ### InfoMem LLM-as-Judge Accuracy: 19.453. Result ID: 6a213c25fbc373592c1ce427. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen2.5-1.5B-Instruct","beta":"0.2"}. This record does not assert independent reproduction. ### Outcome-only GRPO LLM-as-Judge Accuracy: 16.413. Result ID: 6a213c25fbc373592c1ce426. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen2.5-1.5B-Instruct"}. This record does not assert independent reproduction. ### Qwen2.5-1.5B-Instruct LLM-as-Judge Accuracy: 14.59. Result ID: 6a213c25fbc373592c1ce425. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"status":"Base Model"}. This record does not assert independent reproduction. ### ReMemR1 LLM-as-Judge Accuracy: 1.52. Result ID: 6a213c25fbc373592c1ce428. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen2.5-1.5B-Instruct","retrieval":"callback retrieval","framework":"chunk-wise memory-agent"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.