# Long-context Question Answering on MuSiQue (F1) Source: [Long-context Question Answering on MuSiQue (F1)]() Collection index: [llms.txt]() Data updated: 2026-04-10T07:05:17.099Z Evaluation of model performance on the MuSiQue dataset specifically for Long-context Question Answering tasks, measured using the F1 score. 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 Question Answering | | Dataset (including any stated split) | MuSiQue | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 - [F1 Score](): Higher is better; unit: PERCENT. - [SubEM](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | LongMab | 51.02 | Not recorded | 68fa7ac01e209131cea8500a | | LongFaith-PO | 46.35 | Not recorded | 68fa7ac01e209131cea8500a | | LongMab-SFT | 45.62 | Not recorded | 68fa7ac01e209131cea8500a | | Logo-PO | 44.98 | Not recorded | 68fa7ac01e209131cea8500a | | Vanilla LLM | 44.24 | Not recorded | 68fa7ac01e209131cea8500a | | SeaLong-PO | 44.11 | Not recorded | 68fa7ac01e209131cea8500a | | LongReward-PO | 41.94 | Not recorded | 68fa7ac01e209131cea8500a | | LongAlpaca | 38.06 | Not recorded | 68fa7ac01e209131cea8500a | | GLM-4.1V-9B-Thinking VERA | 30.58 | Not recorded | 698d5e64c97a0b3e3b5e3c66 | | GLM-4.1V-9B-Thinking ColPali RAG | 30.24 | Not recorded | 698d5e64c97a0b3e3b5e3c66 | | LongAlign | 28.76 | Not recorded | 68fa7ac01e209131cea8500a | | GLM-4.1V-9B-Thinking Random RAG | 28.71 | Not recorded | 698d5e64c97a0b3e3b5e3c66 | | GLM-4.1V-9B-Thinking Embedding RAG | 28.08 | Not recorded | 698d5e64c97a0b3e3b5e3c66 | | GLM-4.1V-9B-Thinking | 27.85 | Not recorded | 698d5e64c97a0b3e3b5e3c66 | | Glyph | 24.87 | Not recorded | 698d5e64c97a0b3e3b5e3c66 | | Qwen3-VL-8B-Instruct VERA | 17.84 | Not recorded | 698d5e64c97a0b3e3b5e3c66 | | Qwen3-VL-8B-Instruct OCR RAG | 14.7 | Not recorded | 698d5e64c97a0b3e3b5e3c66 | | Qwen3-VL-8B-Instruct Random RAG | 14.68 | Not recorded | 698d5e64c97a0b3e3b5e3c66 | | Qwen3-VL-8B-Instruct | 9.25 | Not recorded | 698d5e64c97a0b3e3b5e3c66 | ### LongMab F1 Score: 51.02. Result ID: 69d8a11247f34ce924c102fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### LongFaith-PO F1 Score: 46.35. Result ID: 69d8a11247f34ce924c102f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### LongMab-SFT F1 Score: 45.62. Result ID: 69d8a11247f34ce924c102f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Logo-PO F1 Score: 44.98. Result ID: 69d8a11247f34ce924c102f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Vanilla LLM F1 Score: 44.24. Result ID: 69d8a11247f34ce924c102f2. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### SeaLong-PO F1 Score: 44.11. Result ID: 69d8a11247f34ce924c102f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### LongReward-PO F1 Score: 41.94. Result ID: 69d8a11247f34ce924c102f6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### LongAlpaca F1 Score: 38.06. Result ID: 69d8a11247f34ce924c102f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### GLM-4.1V-9B-Thinking VERA F1 Score: 30.58. Result ID: 699723a25698665ec471f6a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RAG Strategy":"Attention-Guided RAG"}. This record does not assert independent reproduction. ### GLM-4.1V-9B-Thinking ColPali RAG F1 Score: 30.24. Result ID: 699723a25698665ec471f6a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RAG Strategy":"ColPali RAG"}. This record does not assert independent reproduction. ### LongAlign F1 Score: 28.76. Result ID: 69d8a11247f34ce924c102f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### GLM-4.1V-9B-Thinking Random RAG F1 Score: 28.71. Result ID: 699723a25698665ec471f6a0. [Reporting paper]() Recorded evaluation configuration: {"RAG Strategy":"Random RAG"}. This record does not assert independent reproduction. ### GLM-4.1V-9B-Thinking Embedding RAG F1 Score: 28.08. Result ID: 699723a25698665ec471f6a1. [Reporting paper]() Recorded evaluation configuration: {"RAG Strategy":"Embedding RAG"}. This record does not assert independent reproduction. ### GLM-4.1V-9B-Thinking F1 Score: 27.85. Result ID: 699723a25698665ec471f69f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RAG Strategy":"Direct (None)"}. This record does not assert independent reproduction. ### Glyph F1 Score: 24.87. Result ID: 699723a25698665ec471f6a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RAG Strategy":"Direct (None)"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Instruct VERA F1 Score: 17.84. Result ID: 699723a25698665ec471f6a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RAG Strategy":"Attention-Guided RAG"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Instruct OCR RAG F1 Score: 14.7. Result ID: 699723a25698665ec471f69e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RAG Strategy":"OCR RAG"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Instruct Random RAG F1 Score: 14.68. Result ID: 699723a25698665ec471f69d. [Reporting paper]() Recorded evaluation configuration: {"RAG Strategy":"Random RAG"}. This record does not assert independent reproduction. ### Qwen3-VL-8B-Instruct F1 Score: 9.25. Result ID: 699723a25698665ec471f69c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"RAG Strategy":"Direct (None)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.