# Open-domain Question Answering on 5 QA Benchmarks Average Source: [Open-domain Question Answering on 5 QA Benchmarks Average]() Collection index: [llms.txt]() Data updated: 2026-05-14T07:58:40.020Z Evaluation of model performance on the average of 5 specific Question Answering benchmarks, focusing on Exact Match score and improvement relative to Vanilla RAG. 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 | Open-domain Question Answering | | Dataset (including any stated split) | 5 QA Benchmarks Average | | Metric | Average Exact Match | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Average Exact Match](): Higher is better; unit: PERCENT. - [Avg Improvement vs Vanilla RAG](): Higher is better; unit: SCALAR. ## Recorded results | Method | Average Exact Match | Result date | Report paper | | --- | --- | --- | --- | | PyRAG | 40.9 | Not recorded | 6a0556f0dbc836b87d828b5a | | ITER-RETGEN | 36.3 | Not recorded | 6a0556f0dbc836b87d828b5a | | IRCoT | 34.8 | Not recorded | 6a0556f0dbc836b87d828b5a | | Self-Ask | 32 | Not recorded | 6a0556f0dbc836b87d828b5a | | PyRAG | 30.8 | Not recorded | 6a0556f0dbc836b87d828b5a | | Vanilla RAG | 26.5 | Not recorded | 6a0556f0dbc836b87d828b5a | | ITER-RETGEN | 26.2 | Not recorded | 6a0556f0dbc836b87d828b5a | | IRCoT | 24.7 | Not recorded | 6a0556f0dbc836b87d828b5a | | CoT | 22.5 | Not recorded | 6a0556f0dbc836b87d828b5a | | Self-Ask | 22 | Not recorded | 6a0556f0dbc836b87d828b5a | | Vanilla RAG | 19 | Not recorded | 6a0556f0dbc836b87d828b5a | | Direct Inference | 18.8 | Not recorded | 6a0556f0dbc836b87d828b5a | | Direct Inference | 12 | Not recorded | 6a0556f0dbc836b87d828b5a | | CoT | 10.2 | Not recorded | 6a0556f0dbc836b87d828b5a | ### PyRAG Average Exact Match: 40.9. Result ID: 6a05809f47f34ce924ec4d37. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### ITER-RETGEN Average Exact Match: 36.3. Result ID: 6a05809f47f34ce924ec4d36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### IRCoT Average Exact Match: 34.8. Result ID: 6a05809f47f34ce924ec4d35. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### Self-Ask Average Exact Match: 32. Result ID: 6a05809f47f34ce924ec4d34. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### PyRAG Average Exact Match: 30.8. Result ID: 6a05809f47f34ce924ec4d30. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Vanilla RAG Average Exact Match: 26.5. Result ID: 6a05809f47f34ce924ec4d33. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### ITER-RETGEN Average Exact Match: 26.2. Result ID: 6a05809f47f34ce924ec4d2f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### IRCoT Average Exact Match: 24.7. Result ID: 6a05809f47f34ce924ec4d2e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### CoT Average Exact Match: 22.5. Result ID: 6a05809f47f34ce924ec4d32. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### Self-Ask Average Exact Match: 22. Result ID: 6a05809f47f34ce924ec4d2d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Vanilla RAG Average Exact Match: 19. Result ID: 6a05809f47f34ce924ec4d2c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Direct Inference Average Exact Match: 18.8. Result ID: 6a05809f47f34ce924ec4d31. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-72B-Instruct"}. This record does not assert independent reproduction. ### Direct Inference Average Exact Match: 12. Result ID: 6a05809f47f34ce924ec4d2a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### CoT Average Exact Match: 10.2. Result ID: 6a05809f47f34ce924ec4d2b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.