# Reasoning on BIG-Bench Hard (5 subtasks full) Source: [Reasoning on BIG-Bench Hard (5 subtasks full)]() Collection index: [llms.txt]() Data updated: 2026-05-11T10:03:04.700Z Evaluation of model performance on Reasoning tasks using the specific 5 subtasks subset of the BIG-Bench Hard suite, measured by Accuracy and Gap (NT-T). 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 | Reasoning | | Dataset (including any stated split) | BIG-Bench Hard 5 subtasks (full) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [Gap (NT-T)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Thinking | 86 | Not recorded | 6a0162b8dbc836b87d8232fd | | Nothink | 75.1 | Not recorded | 6a0162b8dbc836b87d8232fd | | Nothink | 75.1 | Not recorded | 6a0162b8dbc836b87d8232fd | | Thinking | 73.6 | Not recorded | 6a0162b8dbc836b87d8232fd | | Nothink | 66.4 | Not recorded | 6a0162b8dbc836b87d8232fd | | Nothink | 49.9 | Not recorded | 6a0162b8dbc836b87d8232fd | | Thinking | 45.8 | Not recorded | 6a0162b8dbc836b87d8232fd | | Thinking | 16.6 | Not recorded | 6a0162b8dbc836b87d8232fd | ### Thinking Accuracy: 86. Result ID: 6a01a95847f34ce924e40f7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Budget":"2048","Backbone":"Qwen3-8B","Thinking Mode":"True"}. This record does not assert independent reproduction. ### Nothink Accuracy: 75.1. Result ID: 6a01a95847f34ce924e40f79. [Reporting paper]() Recorded evaluation configuration: {"Budget":"1024","Backbone":"Qwen3-8B","Thinking Mode":"False"}. This record does not assert independent reproduction. ### Nothink Accuracy: 75.1. Result ID: 6a01a95847f34ce924e40f7b. [Reporting paper]() Recorded evaluation configuration: {"Budget":"2048","Backbone":"Qwen3-8B","Thinking Mode":"False"}. This record does not assert independent reproduction. ### Thinking Accuracy: 73.6. Result ID: 6a01a95847f34ce924e40f7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Budget":"1024","Backbone":"Qwen3-8B","Thinking Mode":"True"}. This record does not assert independent reproduction. ### Nothink Accuracy: 66.4. Result ID: 6a01a95847f34ce924e40f77. [Reporting paper]() Recorded evaluation configuration: {"Budget":"512","Backbone":"Qwen3-8B","Thinking Mode":"False"}. This record does not assert independent reproduction. ### Nothink Accuracy: 49.9. Result ID: 6a01a95847f34ce924e40f75. [Reporting paper]() Recorded evaluation configuration: {"Budget":"256","Backbone":"Qwen3-8B","Thinking Mode":"False"}. This record does not assert independent reproduction. ### Thinking Accuracy: 45.8. Result ID: 6a01a95847f34ce924e40f78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Budget":"512","Backbone":"Qwen3-8B","Thinking Mode":"True"}. This record does not assert independent reproduction. ### Thinking Accuracy: 16.6. Result ID: 6a01a95847f34ce924e40f76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Budget":"256","Backbone":"Qwen3-8B","Thinking Mode":"True"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.