# Bayesian Assessment of Sycophancy on BASIL User belief setting 1.0 (test) Source: [Bayesian Assessment of Sycophancy on BASIL User belief setting 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-04-21T07:04:33.714Z Evaluation of model performance on the Bayesian Assessment of Sycophancy task using the User belief setting 1.0 test split of the BASIL dataset, measured by Bayesian error (RMSE). 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 | Bayesian Assessment of Sycophancy | | Dataset (including any stated split) | BASIL User belief setting 1.0 (test) | | Metric | Bayesian Error (RMSE) | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 18 of 18 | | 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 - [Bayesian Error (RMSE)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Bayesian Error (RMSE) | Result date | Report paper | | --- | --- | --- | --- | | gpt-4o-mini | 0.156 | Not recorded | 68fa7c421e209131cea8d346 | | gpt-4o-mini | 0.184 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:1b | 0.219 | Not recorded | 68fa7c421e209131cea8d346 | | claude-haiku-4-5 | 0.244 | Not recorded | 68fa7c421e209131cea8d346 | | phi-4:14b | 0.246 | Not recorded | 68fa7c421e209131cea8d346 | | gpt-4o-mini | 0.258 | Not recorded | 68fa7c421e209131cea8d346 | | phi-4:14b | 0.273 | Not recorded | 68fa7c421e209131cea8d346 | | claude-haiku-4-5 | 0.273 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:1b | 0.316 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:3b | 0.32 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:3b | 0.33 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:3b | 0.339 | Not recorded | 68fa7c421e209131cea8d346 | | mistral:7b | 0.341 | Not recorded | 68fa7c421e209131cea8d346 | | llama-3.2:1b | 0.366 | Not recorded | 68fa7c421e209131cea8d346 | | mistral:7b | 0.422 | Not recorded | 68fa7c421e209131cea8d346 | | phi-4:14b | 0.425 | Not recorded | 68fa7c421e209131cea8d346 | | claude-haiku-4-5 | 0.476 | Not recorded | 68fa7c421e209131cea8d346 | | mistral:7b | 0.477 | Not recorded | 68fa7c421e209131cea8d346 | ### gpt-4o-mini Bayesian Error (RMSE): 0.156. Result ID: 69e720a447f34ce924cccb53. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### gpt-4o-mini Bayesian Error (RMSE): 0.184. Result ID: 69e720a447f34ce924cccb47. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### llama-3.2:1b Bayesian Error (RMSE): 0.219. Result ID: 69e720a447f34ce924cccb49. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. ### claude-haiku-4-5 Bayesian Error (RMSE): 0.244. Result ID: 69e720a447f34ce924cccb54. [Reporting paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### phi-4:14b Bayesian Error (RMSE): 0.246. Result ID: 69e720a447f34ce924cccb52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### gpt-4o-mini Bayesian Error (RMSE): 0.258. Result ID: 69e720a447f34ce924cccb4d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. ### phi-4:14b Bayesian Error (RMSE): 0.273. Result ID: 69e720a447f34ce924cccb46. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### claude-haiku-4-5 Bayesian Error (RMSE): 0.273. Result ID: 69e720a447f34ce924cccb48. [Reporting paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### llama-3.2:1b Bayesian Error (RMSE): 0.316. Result ID: 69e720a447f34ce924cccb4f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### llama-3.2:3b Bayesian Error (RMSE): 0.32. Result ID: 69e720a447f34ce924cccb50. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### llama-3.2:3b Bayesian Error (RMSE): 0.33. Result ID: 69e720a447f34ce924cccb44. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### llama-3.2:3b Bayesian Error (RMSE): 0.339. Result ID: 69e720a447f34ce924cccb4a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. ### mistral:7b Bayesian Error (RMSE): 0.341. Result ID: 69e720a447f34ce924cccb51. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"5"}. This record does not assert independent reproduction. ### llama-3.2:1b Bayesian Error (RMSE): 0.366. Result ID: 69e720a447f34ce924cccb43. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### mistral:7b Bayesian Error (RMSE): 0.422. Result ID: 69e720a447f34ce924cccb45. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Direct Probing","Number of Samples":"1"}. This record does not assert independent reproduction. ### phi-4:14b Bayesian Error (RMSE): 0.425. Result ID: 69e720a447f34ce924cccb4c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. ### claude-haiku-4-5 Bayesian Error (RMSE): 0.476. Result ID: 69e720a447f34ce924cccb4e. [Reporting paper]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. ### mistral:7b Bayesian Error (RMSE): 0.477. Result ID: 69e720a447f34ce924cccb4b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Confidence Elicitation Method":"Hybrid"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.