# Multi-hop Question Answering on 2WikiMultiHopQA (Speedup) Source: [Multi-hop Question Answering on 2WikiMultiHopQA (Speedup)]() Collection index: [llms.txt]() Data updated: 2026-06-02T10:16:38.312Z Evaluation of model efficiency on the 2WikiMultiHopQA dataset for multi-hop question answering, specifically measuring the speedup factor. 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 | Multi-hop Question Answering | | Dataset (including any stated split) | 2WikiMultiHopQA | | Metric | Speedup Factor | | Unit | SCALAR | | 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 - [Speedup Factor](): Higher is better; unit: SCALAR. ## Recorded results | Method | Speedup Factor | Result date | Report paper | | --- | --- | --- | --- | | Hybrid Verified Decoding | 3.28 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 2.73 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 2.52 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 2.49 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 2.01 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 1.65 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 1.4 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 1.19 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 1.04 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 0.98 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 0.96 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 0.87 | Not recorded | 6a1e63fadbd7150506f85546 | ### Hybrid Verified Decoding Speedup Factor: 3.28. Result ID: 6a1ead43fbc373592c196b07. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-8B","Reference Baseline":"SuffixDecoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 2.73. Result ID: 6a1ead43fbc373592c196b05. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-8B","Reference Baseline":"Greedy Decoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 2.52. Result ID: 6a1ead43fbc373592c196b0d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama3.1-8B","Reference Baseline":"Greedy Decoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 2.49. Result ID: 6a1ead43fbc373592c196b0f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama3.1-8B","Reference Baseline":"SuffixDecoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 2.01. Result ID: 6a1ead43fbc373592c196b09. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-4B","Reference Baseline":"Greedy Decoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 1.65. Result ID: 6a1ead43fbc373592c196b0b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-4B","Reference Baseline":"SuffixDecoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 1.4. Result ID: 6a1ead43fbc373592c196b08. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-8B","Reference Baseline":"Frequency-Based Hybrid Decoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 1.19. Result ID: 6a1ead43fbc373592c196b0a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-4B","Reference Baseline":"EAGLE3"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 1.04. Result ID: 6a1ead43fbc373592c196b0e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama3.1-8B","Reference Baseline":"EAGLE3"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 0.98. Result ID: 6a1ead43fbc373592c196b0c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-4B","Reference Baseline":"Frequency-Based Hybrid Decoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 0.96. Result ID: 6a1ead43fbc373592c196b06. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-8B","Reference Baseline":"EAGLE3"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 0.87. Result ID: 6a1ead43fbc373592c196b10. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama3.1-8B","Reference Baseline":"Frequency-Based Hybrid Decoding"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.