# Fairness Evaluation on Fairness Evaluation Suite (BBQ, CrP, GMO, SSt, WnQ) Source: [Fairness Evaluation on Fairness Evaluation Suite (BBQ, CrP, GMO, SSt, WnQ)]() Collection index: [llms.txt]() Data updated: 2026-07-01T06:38:44.045Z Evaluation of model fairness performance across the aggregated suite of datasets: BBQ, CrP, GMO, SSt, and WnQ, reporting component-wise scores and an overall average. 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 | Fairness Evaluation | | Dataset (including any stated split) | Fairness Evaluation Suite (BBQ, CrP, GMO, SSt, WnQ) | | Metric | BBQ Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 24 of 24 | | 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 - [BBQ Score](): Higher is better; unit: PERCENT. - [CrP Score](): Higher is better; unit: PERCENT. - [GMO Score](): Higher is better; unit: PERCENT. - [SSt Score](): Higher is better; unit: PERCENT. - [WnQ Score](): Higher is better; unit: PERCENT. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | BBQ Score | Result date | Report paper | | --- | --- | --- | --- | | SD-E | 98.26 | Not recorded | 6a449f01e0224bd4f4992f95 | | ADBP | 97.99 | Not recorded | 6a449f01e0224bd4f4992f95 | | RP 2 | 97.99 | Not recorded | 6a449f01e0224bd4f4992f95 | | Fair-GCG | 97.9 | Not recorded | 6a449f01e0224bd4f4992f95 | | Luo et al. | 97.8 | Not recorded | 6a449f01e0224bd4f4992f95 | | SR 2 | 96.89 | Not recorded | 6a449f01e0224bd4f4992f95 | | SR 3 | 96.89 | Not recorded | 6a449f01e0224bd4f4992f95 | | Vanilla | 96.25 | Not recorded | 6a449f01e0224bd4f4992f95 | | RP 1 | 96.16 | Not recorded | 6a449f01e0224bd4f4992f95 | | IASC | 95.61 | Not recorded | 6a449f01e0224bd4f4992f95 | | SR 1 | 95.52 | Not recorded | 6a449f01e0224bd4f4992f95 | | SD-R | 94.51 | Not recorded | 6a449f01e0224bd4f4992f95 | | Luo et al. | 91.95 | Not recorded | 6a449f01e0224bd4f4992f95 | | SD-E | 90.85 | Not recorded | 6a449f01e0224bd4f4992f95 | | ADBP | 84.81 | Not recorded | 6a449f01e0224bd4f4992f95 | | SD-R | 82.53 | Not recorded | 6a449f01e0224bd4f4992f95 | | Fair-GCG | 81.34 | Not recorded | 6a449f01e0224bd4f4992f95 | | RP 2 | 79.14 | Not recorded | 6a449f01e0224bd4f4992f95 | | Vanilla | 74.38 | Not recorded | 6a449f01e0224bd4f4992f95 | | RP 1 | 73.47 | Not recorded | 6a449f01e0224bd4f4992f95 | | IASC | 72.92 | Not recorded | 6a449f01e0224bd4f4992f95 | | SR 3 | 69.35 | Not recorded | 6a449f01e0224bd4f4992f95 | | SR 2 | 67.7 | Not recorded | 6a449f01e0224bd4f4992f95 | | SR 1 | 63.22 | Not recorded | 6a449f01e0224bd4f4992f95 | ### SD-E BBQ Score: 98.26. Result ID: 6a44b5f373d097d845bd9189. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### ADBP BBQ Score: 97.99. Result ID: 6a44b5f373d097d845bd9187. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### RP 2 BBQ Score: 97.99. Result ID: 6a44b5f373d097d845bd918c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### Fair-GCG BBQ Score: 97.9. Result ID: 6a44b5f373d097d845bd9190. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### Luo et al. BBQ Score: 97.8. Result ID: 6a44b5f373d097d845bd9186. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### SR 2 BBQ Score: 96.89. Result ID: 6a44b5f373d097d845bd918e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### SR 3 BBQ Score: 96.89. Result ID: 6a44b5f373d097d845bd918f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### Vanilla BBQ Score: 96.25. Result ID: 6a44b5f373d097d845bd9185. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### RP 1 BBQ Score: 96.16. Result ID: 6a44b5f373d097d845bd918b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### IASC BBQ Score: 95.61. Result ID: 6a44b5f373d097d845bd9188. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### SR 1 BBQ Score: 95.52. Result ID: 6a44b5f373d097d845bd918d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### SD-R BBQ Score: 94.51. Result ID: 6a44b5f373d097d845bd918a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5 7B"}. This record does not assert independent reproduction. ### Luo et al. BBQ Score: 91.95. Result ID: 6a44b5f373d097d845bd917a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. ### SD-E BBQ Score: 90.85. Result ID: 6a44b5f373d097d845bd917d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. ### ADBP BBQ Score: 84.81. Result ID: 6a44b5f373d097d845bd917b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. ### SD-R BBQ Score: 82.53. Result ID: 6a44b5f373d097d845bd917e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. ### Fair-GCG BBQ Score: 81.34. Result ID: 6a44b5f373d097d845bd9184. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. ### RP 2 BBQ Score: 79.14. Result ID: 6a44b5f373d097d845bd9180. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. ### Vanilla BBQ Score: 74.38. Result ID: 6a44b5f373d097d845bd9179. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. ### RP 1 BBQ Score: 73.47. Result ID: 6a44b5f373d097d845bd917f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. ### IASC BBQ Score: 72.92. Result ID: 6a44b5f373d097d845bd917c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. ### SR 3 BBQ Score: 69.35. Result ID: 6a44b5f373d097d845bd9183. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. ### SR 2 BBQ Score: 67.7. Result ID: 6a44b5f373d097d845bd9182. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. ### SR 1 BBQ Score: 63.22. Result ID: 6a44b5f373d097d845bd9181. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.1 8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.