# Honesty Alignment on HonestyBench In-Domain Source: [Honesty Alignment on HonestyBench In-Domain]() Collection index: [llms.txt]() Data updated: 2026-03-05T06:57:19.060Z Evaluation of model performance on the Honesty Alignment task using the In-Domain split of the HonestyBench dataset, measured by NQ, TQ, HQ, 2Wiki, and Pararel scores. 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 | Honesty Alignment | | Dataset (including any stated split) | HonestyBench In-Domain | | Metric | NQ Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [NQ Score](): Higher is better; unit: PERCENT. - [TQ Score](): Higher is better; unit: PERCENT. - [HQ Score](): Higher is better; unit: PERCENT. - [2Wiki Score](): Higher is better; unit: PERCENT. - [Pararel Score](): Higher is better; unit: PERCENT. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | NQ Score | Result date | Report paper | | --- | --- | --- | --- | | EliCal | 85.16 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | Cal-Only | 84.89 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | EliCal | 82.38 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | Consis-Sem | 80.68 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | Eli-Only | 77.86 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | Cal-Only | 72.19 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | Verbal-10 | 68.82 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | N-Prob | 66.11 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | Consis-Lex | 65.02 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | Verbal-0 | 64.02 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | DACA | 61.69 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | Thermometer | 58.15 | Not recorded | 68fa7c5b1e209131cea8dbc1 | | Prob | 56.79 | Not recorded | 68fa7c5b1e209131cea8dbc1 | ### EliCal NQ Score: 85.16. Result ID: 69a928b36dbb7075b951f964. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Upper Bound","Amount of annotated data":"560k","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Cal-Only NQ Score: 84.89. Result ID: 69a928b36dbb7075b951f963. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Upper Bound","Amount of annotated data":"560k","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### EliCal NQ Score: 82.38. Result ID: 69a928b36dbb7075b951f962. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Training-based","Amount of annotated data":"1k","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Consis-Sem NQ Score: 80.68. Result ID: 69a928b36dbb7075b951f95d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Training-free","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Eli-Only NQ Score: 77.86. Result ID: 69a928b36dbb7075b951f960. [Reporting paper]() Recorded evaluation configuration: {"Category":"Training-based","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Cal-Only NQ Score: 72.19. Result ID: 69a928b36dbb7075b951f961. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Training-based","Amount of annotated data":"1k","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Verbal-10 NQ Score: 68.82. Result ID: 69a928b36dbb7075b951f95b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Training-free","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### N-Prob NQ Score: 66.11. Result ID: 69a928b36dbb7075b951f959. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Training-free","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Consis-Lex NQ Score: 65.02. Result ID: 69a928b36dbb7075b951f95c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Training-free","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Verbal-0 NQ Score: 64.02. Result ID: 69a928b36dbb7075b951f95a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Training-free","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### DACA NQ Score: 61.69. Result ID: 69a928b36dbb7075b951f95f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Training-based","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Thermometer NQ Score: 58.15. Result ID: 69a928b36dbb7075b951f95e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Training-based","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Prob NQ Score: 56.79. Result ID: 69a928b36dbb7075b951f958. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Training-free","Base Model":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.