# Mathematical Reasoning on AMC 23 (LLM Trust Score) Source: [Mathematical Reasoning on AMC 23 (LLM Trust Score)]() Collection index: [llms.txt]() Data updated: 2026-05-22T09:16:41.430Z Evaluation of model performance on the AMC 23 dataset for Mathematical Reasoning tasks, measured using the LLM Trust Score metric. 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 | Mathematical Reasoning | | Dataset (including any stated split) | AMC 23 | | Metric | LLM Trust Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [LLM Trust Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | LLM Trust Score | Result date | Report paper | | --- | --- | --- | --- | | DecepChain | 98.5 | Not recorded | 68fa7bc31e209131cea8a40f | | DecepChain | 96.5 | Not recorded | 68fa7bc31e209131cea8a40f | | DecepChain | 92.5 | Not recorded | 68fa7bc31e209131cea8a40f | | DecepChain | 86 | Not recorded | 68fa7bc31e209131cea8a40f | | BadNet | 75 | Not recorded | 68fa7bc31e209131cea8a40f | | BadNet | 74.5 | Not recorded | 68fa7bc31e209131cea8a40f | | BadNet | 65.5 | Not recorded | 68fa7bc31e209131cea8a40f | | DTCoT | 63.5 | Not recorded | 68fa7bc31e209131cea8a40f | | BadChain | 62 | Not recorded | 68fa7bc31e209131cea8a40f | | BadNet | 42 | Not recorded | 68fa7bc31e209131cea8a40f | | BadChain | 32.5 | Not recorded | 68fa7bc31e209131cea8a40f | | DTCoT | 23 | Not recorded | 68fa7bc31e209131cea8a40f | | BadChain | 6.5 | Not recorded | 68fa7bc31e209131cea8a40f | | DTCoT | 3.5 | Not recorded | 68fa7bc31e209131cea8a40f | | BadChain | 3.5 | Not recorded | 68fa7bc31e209131cea8a40f | | DTCoT | 3 | Not recorded | 68fa7bc31e209131cea8a40f | ### DecepChain LLM Trust Score: 98.5. Result ID: 6a101e2efbc373592c095dce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. ### DecepChain LLM Trust Score: 96.5. Result ID: 6a101e2efbc373592c095dca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction. ### DecepChain LLM Trust Score: 92.5. Result ID: 6a101e2efbc373592c095dc6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### DecepChain LLM Trust Score: 86. Result ID: 6a101e2efbc373592c095dc2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-1.5B"}. This record does not assert independent reproduction. ### BadNet LLM Trust Score: 75. Result ID: 6a101e2efbc373592c095dcb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. ### BadNet LLM Trust Score: 74.5. Result ID: 6a101e2efbc373592c095dc3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### BadNet LLM Trust Score: 65.5. Result ID: 6a101e2efbc373592c095dbf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-1.5B"}. This record does not assert independent reproduction. ### DTCoT LLM Trust Score: 63.5. Result ID: 6a101e2efbc373592c095dc8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction. ### BadChain LLM Trust Score: 62. Result ID: 6a101e2efbc373592c095dc9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction. ### BadNet LLM Trust Score: 42. Result ID: 6a101e2efbc373592c095dc7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction. ### BadChain LLM Trust Score: 32.5. Result ID: 6a101e2efbc373592c095dc1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-1.5B"}. This record does not assert independent reproduction. ### DTCoT LLM Trust Score: 23. Result ID: 6a101e2efbc373592c095dc0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-1.5B"}. This record does not assert independent reproduction. ### BadChain LLM Trust Score: 6.5. Result ID: 6a101e2efbc373592c095dcd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. ### DTCoT LLM Trust Score: 3.5. Result ID: 6a101e2efbc373592c095dc4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### BadChain LLM Trust Score: 3.5. Result ID: 6a101e2efbc373592c095dc5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### DTCoT LLM Trust Score: 3. Result ID: 6a101e2efbc373592c095dcc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.2-3B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.