# LLM Judging on JudgeBench (GPT-4o 1.0 Generated Responses) Source: [LLM Judging on JudgeBench (GPT-4o 1.0 Generated Responses)]() Collection index: [llms.txt]() Data updated: 2026-05-13T07:44:02.478Z Evaluation of LLM performance using the LLM Judging methodology on response pairs generated specifically by GPT-4o 1.0, reporting scores across Knowledge, Reasoning, Math, and Coding dimensions. 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 Judging | | Dataset (including any stated split) | JudgeBench response pairs generated by GPT-4o 1.0 | | Metric | Knowledge | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [Knowledge](): Higher is better; unit: PERCENT. - [Reasoning](): Higher is better; unit: PERCENT. - [Math](): Higher is better; unit: PERCENT. - [Coding](): Higher is better; unit: PERCENT. - [Overall Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Knowledge | Result date | Report paper | | --- | --- | --- | --- | | GPT-4O | 68.18 | Not recorded | 68fa77601e209131cea72d17 | | CLAUDE-3.5-SONNET | 62.99 | Not recorded | 68fa77601e209131cea72d17 | | GPT-4O | 61.04 | Not recorded | 68fa77601e209131cea72d17 | | CLAUDE-3.5-SONNET | 59.74 | Not recorded | 68fa77601e209131cea72d17 | | GEMINI-1.5-PRO | 57.79 | Not recorded | 68fa77601e209131cea72d17 | | GEMINI-1.5-PRO | 56.49 | Not recorded | 68fa77601e209131cea72d17 | | GPT-4O-MINI | 46.75 | Not recorded | 68fa77601e209131cea72d17 | | GPT-4O | 46.1 | Not recorded | 68fa77601e209131cea72d17 | | GEMINI-1.5-PRO | 45.45 | Not recorded | 68fa77601e209131cea72d17 | | GEMINI-1.5-FLASH | 26.62 | Not recorded | 68fa77601e209131cea72d17 | | CLAUDE-3-HAIKU | 20.78 | Not recorded | 68fa77601e209131cea72d17 | ### GPT-4O Knowledge: 68.18. Result ID: 6a042bbb47f34ce924e9cc0d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Version":"2024-11-20","Prompting Goal":"reverse goal","Strategy":"SOP prompting"}. This record does not assert independent reproduction. ### CLAUDE-3.5-SONNET Knowledge: 62.99. Result ID: 6a042bbb47f34ce924e9cc0f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Version":"2024-06-20","Prompting Goal":"reverse goal","Strategy":"SOP prompting"}. This record does not assert independent reproduction. ### GPT-4O Knowledge: 61.04. Result ID: 6a042bbb47f34ce924e9cc07. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Version":"2024-11-20","Prompting Goal":"original goal"}. This record does not assert independent reproduction. ### CLAUDE-3.5-SONNET Knowledge: 59.74. Result ID: 6a042bbb47f34ce924e9cc0c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Version":"2024-06-20","Prompting Goal":"original goal","Evaluation Protocol":"strict two-trial"}. This record does not assert independent reproduction. ### GEMINI-1.5-PRO Knowledge: 57.79. Result ID: 6a042bbb47f34ce924e9cc0a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Version":"002","Prompting Goal":"original goal"}. This record does not assert independent reproduction. ### GEMINI-1.5-PRO Knowledge: 56.49. Result ID: 6a042bbb47f34ce924e9cc0e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Version":"002","Prompting Goal":"reverse goal","Strategy":"SOP prompting"}. This record does not assert independent reproduction. ### GPT-4O-MINI Knowledge: 46.75. Result ID: 6a042bbb47f34ce924e9cc05. [Reporting paper]() Recorded evaluation configuration: {"Version":"2024-07-18","Prompting Goal":"original goal","Evaluation Protocol":"strict two-trial"}. This record does not assert independent reproduction. ### GPT-4O Knowledge: 46.1. Result ID: 6a042bbb47f34ce924e9cc06. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Version":"2024-05-13","Prompting Goal":"original goal","Evaluation Protocol":"strict two-trial"}. This record does not assert independent reproduction. ### GEMINI-1.5-PRO Knowledge: 45.45. Result ID: 6a042bbb47f34ce924e9cc09. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Version":"001","Prompting Goal":"original goal","Evaluation Protocol":"strict two-trial"}. This record does not assert independent reproduction. ### GEMINI-1.5-FLASH Knowledge: 26.62. Result ID: 6a042bbb47f34ce924e9cc08. [Reporting paper]() Recorded evaluation configuration: {"Version":"001","Prompting Goal":"original goal","Evaluation Protocol":"strict two-trial"}. This record does not assert independent reproduction. ### CLAUDE-3-HAIKU Knowledge: 20.78. Result ID: 6a042bbb47f34ce924e9cc0b. [Reporting paper]() Recorded evaluation configuration: {"Version":"2024-03-07","Prompting Goal":"original goal","Evaluation Protocol":"strict two-trial"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.