# Judge Agreement Accuracy on Quora 915 queries (test) Source: [Judge Agreement Accuracy on Quora 915 queries (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:46.751Z Evaluation of model agreement accuracy when judging responses based on the Quora 915 queries test set, measured using Agreement accuracy (%). 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 | Judge Agreement Accuracy | | Dataset (including any stated split) | Quora 915 queries (test) | | Metric | Agreement Accuracy | | 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 - [Agreement Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Agreement Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LogicJudge | 73 | Not recorded | 699d30576017c4460ffab1d5 | | Ensemble Vote | 71.31 | Not recorded | 699d30576017c4460ffab1d5 | | gpt-5 | 70.33 | Not recorded | 699d30576017c4460ffab1d5 | | gemini-2.5-pro | 70 | Not recorded | 699d30576017c4460ffab1d5 | | gpt-o3 | 69.67 | Not recorded | 699d30576017c4460ffab1d5 | | qwen3-max | 69.67 | Not recorded | 699d30576017c4460ffab1d5 | | gemini-2.5-pro | 68 | Not recorded | 699d30576017c4460ffab1d5 | | claude-4.5-sonnet | 68 | Not recorded | 699d30576017c4460ffab1d5 | | gpt-5.1 | 66 | Not recorded | 699d30576017c4460ffab1d5 | | claude-4.5-sonnet | 66 | Not recorded | 699d30576017c4460ffab1d5 | | gemini-3-pro | 65 | Not recorded | 699d30576017c4460ffab1d5 | | gemini-3-pro | 62.33 | Not recorded | 699d30576017c4460ffab1d5 | | Ensemble Consensus | 56.67 | Not recorded | 699d30576017c4460ffab1d5 | | qwen3-235b | 53.67 | Not recorded | 699d30576017c4460ffab1d5 | | deepseek-v3 | 53.33 | Not recorded | 699d30576017c4460ffab1d5 | | claude-4-sonnet | 51.67 | Not recorded | 699d30576017c4460ffab1d5 | | claude-4-sonnet | 51.33 | Not recorded | 699d30576017c4460ffab1d5 | | qwen-max | 40.67 | Not recorded | 699d30576017c4460ffab1d5 | | gpt-4.1 | 34 | Not recorded | 699d30576017c4460ffab1d5 | ### LogicJudge Agreement Accuracy: 73. Result ID: 699e14275698665ec4cc7930. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"backbone":"Qwen-3-30B-A3B","training":"SFT + GRPO"}. This record does not assert independent reproduction. ### Ensemble Vote Agreement Accuracy: 71.31. Result ID: 699e14275698665ec4cc792f. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### gpt-5 Agreement Accuracy: 70.33. Result ID: 699e14275698665ec4cc7920. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### gemini-2.5-pro Agreement Accuracy: 70. Result ID: 699e14275698665ec4cc7922. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### gpt-o3 Agreement Accuracy: 69.67. Result ID: 699e14275698665ec4cc791e. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### qwen3-max Agreement Accuracy: 69.67. Result ID: 699e14275698665ec4cc792a. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### gemini-2.5-pro Agreement Accuracy: 68. Result ID: 699e14275698665ec4cc7923. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot","mode":"thinking"}. This record does not assert independent reproduction. ### claude-4.5-sonnet Agreement Accuracy: 68. Result ID: 699e14275698665ec4cc7928. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### gpt-5.1 Agreement Accuracy: 66. Result ID: 699e14275698665ec4cc7921. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### claude-4.5-sonnet Agreement Accuracy: 66. Result ID: 699e14275698665ec4cc7929. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot","mode":"thinking"}. This record does not assert independent reproduction. ### gemini-3-pro Agreement Accuracy: 65. Result ID: 699e14275698665ec4cc7925. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot","mode":"thinking"}. This record does not assert independent reproduction. ### gemini-3-pro Agreement Accuracy: 62.33. Result ID: 699e14275698665ec4cc7924. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### Ensemble Consensus Agreement Accuracy: 56.67. Result ID: 699e14275698665ec4cc792e. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### qwen3-235b Agreement Accuracy: 53.67. Result ID: 699e14275698665ec4cc792c. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### deepseek-v3 Agreement Accuracy: 53.33. Result ID: 699e14275698665ec4cc792d. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### claude-4-sonnet Agreement Accuracy: 51.67. Result ID: 699e14275698665ec4cc7926. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### claude-4-sonnet Agreement Accuracy: 51.33. Result ID: 699e14275698665ec4cc7927. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot","mode":"thinking"}. This record does not assert independent reproduction. ### qwen-max Agreement Accuracy: 40.67. Result ID: 699e14275698665ec4cc792b. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. ### gpt-4.1 Agreement Accuracy: 34. Result ID: 699e14275698665ec4cc791f. [Reporting paper]() Recorded evaluation configuration: {"evaluation\_setting":"one-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.