# LLM-as-a-judge on AlpacaEval Source: [LLM-as-a-judge on AlpacaEval]() Collection index: [llms.txt]() Data updated: 2026-05-18T07:07:51.651Z Evaluation of LLM performance using the AlpacaEval dataset, measured by Coverage and Success rates. 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 | LLM-as-a-judge | | Dataset (including any stated split) | AlpacaEval | | Metric | Coverage | | 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 - [Coverage](): Higher is better; unit: PERCENT. - [Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Coverage | Result date | Report paper | | --- | --- | --- | --- | | Heuristic Selection | 78.3 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | | Heuristic Selection | 74.5 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | | CSE + Predictive | 54.5 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | | CSE + Ours | 54.5 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | | CSE + Simulated | 52.6 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | | CSE + Vanilla | 52 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | | CSE + Random | 48.7 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | | CSE + Ours | 38.4 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | | CSE + Predictive | 37.6 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | | CSE + Vanilla | 34.6 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | | CSE + Simulated | 34.1 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | | CSE + Random | 33.2 | Not recorded | 6a0a9d11dbc836b87d82b3e2 | ### Heuristic Selection Coverage: 78.3. Result ID: 6a0abaae47f34ce924f05db3. [Reporting paper]() Recorded evaluation configuration: {"Cascade":"M → L → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. ### Heuristic Selection Coverage: 74.5. Result ID: 6a0abaae47f34ce924f05dad. [Reporting paper]() Recorded evaluation configuration: {"Cascade":"L → Q → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. ### CSE + Predictive Coverage: 54.5. Result ID: 6a0abaae47f34ce924f05db4. [Reporting paper]() Recorded evaluation configuration: {"Cascade":"M → L → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. ### CSE + Ours Coverage: 54.5. Result ID: 6a0abaae47f34ce924f05db8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cascade":"M → L → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. ### CSE + Simulated Coverage: 52.6. Result ID: 6a0abaae47f34ce924f05db5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cascade":"M → L → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. ### CSE + Vanilla Coverage: 52. Result ID: 6a0abaae47f34ce924f05db7. [Reporting paper]() Recorded evaluation configuration: {"Cascade":"M → L → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. ### CSE + Random Coverage: 48.7. Result ID: 6a0abaae47f34ce924f05db6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cascade":"M → L → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. ### CSE + Ours Coverage: 38.4. Result ID: 6a0abaae47f34ce924f05db2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cascade":"L → Q → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. ### CSE + Predictive Coverage: 37.6. Result ID: 6a0abaae47f34ce924f05dae. [Reporting paper]() Recorded evaluation configuration: {"Cascade":"L → Q → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. ### CSE + Vanilla Coverage: 34.6. Result ID: 6a0abaae47f34ce924f05db1. [Reporting paper]() Recorded evaluation configuration: {"Cascade":"L → Q → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. ### CSE + Simulated Coverage: 34.1. Result ID: 6a0abaae47f34ce924f05daf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cascade":"L → Q → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. ### CSE + Random Coverage: 33.2. Result ID: 6a0abaae47f34ce924f05db0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cascade":"L → Q → O","Target agreement level":"0.85"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.