# opt-66b

## opt-66b.json
|                      Task                       |Version| Metric |Value|   |Stderr|
|-------------------------------------------------|------:|--------|----:|---|-----:|
|arc_challenge                                    |      0|acc     |37.20|±  |  1.41|
|                                                 |       |acc_norm|40.10|±  |  1.43|
|arc_easy                                         |      0|acc     |71.68|±  |  0.92|
|                                                 |       |acc_norm|67.30|±  |  0.96|
|hendrycksTest-abstract_algebra                   |      0|acc     |23.00|±  |  4.23|
|                                                 |       |acc_norm|24.00|±  |  4.29|
|hendrycksTest-anatomy                            |      0|acc     |27.41|±  |  3.85|
|                                                 |       |acc_norm|26.67|±  |  3.82|
|hendrycksTest-astronomy                          |      0|acc     |28.95|±  |  3.69|
|                                                 |       |acc_norm|40.13|±  |  3.99|
|hendrycksTest-business_ethics                    |      0|acc     |29.00|±  |  4.56|
|                                                 |       |acc_norm|28.00|±  |  4.51|
|hendrycksTest-clinical_knowledge                 |      0|acc     |24.15|±  |  2.63|
|                                                 |       |acc_norm|27.55|±  |  2.75|
|hendrycksTest-college_biology                    |      0|acc     |24.31|±  |  3.59|
|                                                 |       |acc_norm|25.00|±  |  3.62|
|hendrycksTest-college_chemistry                  |      0|acc     |30.00|±  |  4.61|
|                                                 |       |acc_norm|34.00|±  |  4.76|
|hendrycksTest-college_computer_science           |      0|acc     |23.00|±  |  4.23|
|                                                 |       |acc_norm|28.00|±  |  4.51|
|hendrycksTest-college_mathematics                |      0|acc     |23.00|±  |  4.23|
|                                                 |       |acc_norm|29.00|±  |  4.56|
|hendrycksTest-college_medicine                   |      0|acc     |23.70|±  |  3.24|
|                                                 |       |acc_norm|24.86|±  |  3.30|
|hendrycksTest-college_physics                    |      0|acc     |28.43|±  |  4.49|
|                                                 |       |acc_norm|26.47|±  |  4.39|
|hendrycksTest-computer_security                  |      0|acc     |32.00|±  |  4.69|
|                                                 |       |acc_norm|29.00|±  |  4.56|
|hendrycksTest-conceptual_physics                 |      0|acc     |25.53|±  |  2.85|
|                                                 |       |acc_norm|22.98|±  |  2.75|
|hendrycksTest-econometrics                       |      0|acc     |28.07|±  |  4.23|
|                                                 |       |acc_norm|20.18|±  |  3.78|
|hendrycksTest-electrical_engineering             |      0|acc     |35.86|±  |  4.00|
|                                                 |       |acc_norm|38.62|±  |  4.06|
|hendrycksTest-elementary_mathematics             |      0|acc     |26.46|±  |  2.27|
|                                                 |       |acc_norm|27.25|±  |  2.29|
|hendrycksTest-formal_logic                       |      0|acc     |30.16|±  |  4.10|
|                                                 |       |acc_norm|28.57|±  |  4.04|
|hendrycksTest-global_facts                       |      0|acc     |29.00|±  |  4.56|
|                                                 |       |acc_norm|26.00|±  |  4.41|
|hendrycksTest-high_school_biology                |      0|acc     |26.13|±  |  2.50|
|                                                 |       |acc_norm|31.94|±  |  2.65|
|hendrycksTest-high_school_chemistry              |      0|acc     |24.14|±  |  3.01|
|                                                 |       |acc_norm|34.48|±  |  3.34|
|hendrycksTest-high_school_computer_science       |      0|acc     |31.00|±  |  4.65|
|                                                 |       |acc_norm|30.00|±  |  4.61|
|hendrycksTest-high_school_european_history       |      0|acc     |29.09|±  |  3.55|
|                                                 |       |acc_norm|29.70|±  |  3.57|
|hendrycksTest-high_school_geography              |      0|acc     |26.26|±  |  3.14|
|                                                 |       |acc_norm|31.82|±  |  3.32|
|hendrycksTest-high_school_government_and_politics|      0|acc     |26.42|±  |  3.18|
|                                                 |       |acc_norm|26.42|±  |  3.18|
|hendrycksTest-high_school_macroeconomics         |      0|acc     |29.49|±  |  2.31|
|                                                 |       |acc_norm|26.67|±  |  2.24|
|hendrycksTest-high_school_mathematics            |      0|acc     |21.85|±  |  2.52|
|                                                 |       |acc_norm|32.22|±  |  2.85|
|hendrycksTest-high_school_microeconomics         |      0|acc     |29.83|±  |  2.97|
|                                                 |       |acc_norm|36.13|±  |  3.12|
|hendrycksTest-high_school_physics                |      0|acc     |22.52|±  |  3.41|
|                                                 |       |acc_norm|23.18|±  |  3.45|
|hendrycksTest-high_school_psychology             |      0|acc     |28.44|±  |  1.93|
|                                                 |       |acc_norm|25.87|±  |  1.88|
|hendrycksTest-high_school_statistics             |      0|acc     |29.17|±  |  3.10|
|                                                 |       |acc_norm|33.33|±  |  3.21|
|hendrycksTest-high_school_us_history             |      0|acc     |27.45|±  |  3.13|
|                                                 |       |acc_norm|30.39|±  |  3.23|
|hendrycksTest-high_school_world_history          |      0|acc     |30.80|±  |  3.01|
|                                                 |       |acc_norm|32.49|±  |  3.05|
|hendrycksTest-human_aging                        |      0|acc     |28.70|±  |  3.04|
|                                                 |       |acc_norm|22.42|±  |  2.80|
|hendrycksTest-human_sexuality                    |      0|acc     |36.64|±  |  4.23|
|                                                 |       |acc_norm|32.82|±  |  4.12|
|hendrycksTest-international_law                  |      0|acc     |25.62|±  |  3.98|
|                                                 |       |acc_norm|49.59|±  |  4.56|
|hendrycksTest-jurisprudence                      |      0|acc     |30.56|±  |  4.45|
|                                                 |       |acc_norm|42.59|±  |  4.78|
|hendrycksTest-logical_fallacies                  |      0|acc     |23.93|±  |  3.35|
|                                                 |       |acc_norm|28.83|±  |  3.56|
|hendrycksTest-machine_learning                   |      0|acc     |24.11|±  |  4.06|
|                                                 |       |acc_norm|23.21|±  |  4.01|
|hendrycksTest-management                         |      0|acc     |29.13|±  |  4.50|
|                                                 |       |acc_norm|33.98|±  |  4.69|
|hendrycksTest-marketing                          |      0|acc     |29.06|±  |  2.97|
|                                                 |       |acc_norm|29.06|±  |  2.97|
|hendrycksTest-medical_genetics                   |      0|acc     |34.00|±  |  4.76|
|                                                 |       |acc_norm|45.00|±  |  5.00|
|hendrycksTest-miscellaneous                      |      0|acc     |32.69|±  |  1.68|
|                                                 |       |acc_norm|29.37|±  |  1.63|
|hendrycksTest-moral_disputes                     |      0|acc     |32.08|±  |  2.51|
|                                                 |       |acc_norm|31.79|±  |  2.51|
|hendrycksTest-moral_scenarios                    |      0|acc     |22.12|±  |  1.39|
|                                                 |       |acc_norm|27.26|±  |  1.49|
|hendrycksTest-nutrition                          |      0|acc     |33.33|±  |  2.70|
|                                                 |       |acc_norm|39.54|±  |  2.80|
|hendrycksTest-philosophy                         |      0|acc     |25.08|±  |  2.46|
|                                                 |       |acc_norm|35.05|±  |  2.71|
|hendrycksTest-prehistory                         |      0|acc     |24.38|±  |  2.39|
|                                                 |       |acc_norm|21.30|±  |  2.28|
|hendrycksTest-professional_accounting            |      0|acc     |20.21|±  |  2.40|
|                                                 |       |acc_norm|22.70|±  |  2.50|
|hendrycksTest-professional_law                   |      0|acc     |27.90|±  |  1.15|
|                                                 |       |acc_norm|29.53|±  |  1.17|
|hendrycksTest-professional_medicine              |      0|acc     |26.47|±  |  2.68|
|                                                 |       |acc_norm|29.78|±  |  2.78|
|hendrycksTest-professional_psychology            |      0|acc     |26.14|±  |  1.78|
|                                                 |       |acc_norm|28.59|±  |  1.83|
|hendrycksTest-public_relations                   |      0|acc     |34.55|±  |  4.55|
|                                                 |       |acc_norm|15.45|±  |  3.46|
|hendrycksTest-security_studies                   |      0|acc     |38.37|±  |  3.11|
|                                                 |       |acc_norm|32.65|±  |  3.00|
|hendrycksTest-sociology                          |      0|acc     |28.86|±  |  3.20|
|                                                 |       |acc_norm|27.36|±  |  3.15|
|hendrycksTest-us_foreign_policy                  |      0|acc     |37.00|±  |  4.85|
|                                                 |       |acc_norm|36.00|±  |  4.82|
|hendrycksTest-virology                           |      0|acc     |32.53|±  |  3.65|
|                                                 |       |acc_norm|30.12|±  |  3.57|
|hendrycksTest-world_religions                    |      0|acc     |33.92|±  |  3.63|
|                                                 |       |acc_norm|37.43|±  |  3.71|
|lambada_openai                                   |      0|ppl     | 3.29|±  |  0.06|
|                                                 |       |acc     |73.90|±  |  0.61|
|logiqa                                           |      0|acc     |22.73|±  |  1.64|
|                                                 |       |acc_norm|28.73|±  |  1.77|
|piqa                                             |      0|acc     |78.78|±  |  0.95|
|                                                 |       |acc_norm|79.87|±  |  0.94|
|sciq                                             |      0|acc     |92.60|±  |  0.83|
|                                                 |       |acc_norm|87.30|±  |  1.05|
|winogrande                                       |      0|acc     |68.75|±  |  1.30|
|wsc                                              |      0|acc     |54.81|±  |  4.90|