# Opponent modeling on CaSiNo (External) Source: [Opponent modeling on CaSiNo (External)]() Collection index: [llms.txt]() Data updated: 2026-05-07T08:36:17.758Z Evaluation of opponent modeling performance on the CaSiNo (External) dataset, typically measured using EMA, Top-1 accuracy, and NDCG@3. 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 | Opponent modeling | | Dataset (including any stated split) | CaSiNo (External) | | Metric | EMA | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [EMA](): Higher is better; unit: SCALAR. - [Top-1 Accuracy](): Higher is better; unit: PERCENT. - [NDCG@3](): Higher is better; unit: PERCENT. ## Recorded results | Method | EMA | Result date | Report paper | | --- | --- | --- | --- | | BOND | 53.84 | Not recorded | 69fc1cac5497b3b670c88621 | | RoBERTa CD+CA+DND | 48.72 | Not recorded | 69fc1cac5497b3b670c88621 | | BERT CD+CA+DND | 44.22 | Not recorded | 69fc1cac5497b3b670c88621 | | 70B structured-CoT prompted | 37.3 | Not recorded | 69fc1cac5497b3b670c88621 | | BoW-Ranker | 27.71 | Not recorded | 69fc1cac5497b3b670c88621 | ### BOND EMA: 53.84. Result ID: 69fc4e6447f34ce924df0567. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training strategy":"Supervised SFT","Model scale":"8B","Evaluation protocol":"k-penalty"}. This record does not assert independent reproduction. ### RoBERTa CD+CA+DND EMA: 48.72. Result ID: 69fc4e6447f34ce924df0565. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"k-penalty"}. This record does not assert independent reproduction. ### BERT CD+CA+DND EMA: 44.22. Result ID: 69fc4e6447f34ce924df0564. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"k-penalty"}. This record does not assert independent reproduction. ### 70B structured-CoT prompted EMA: 37.3. Result ID: 69fc4e6447f34ce924df0566. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model scale":"70B","Strategy":"Prompted","Evaluation protocol":"k-penalty"}. This record does not assert independent reproduction. ### BoW-Ranker EMA: 27.71. Result ID: 69fc4e6447f34ce924df0563. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation protocol":"k-penalty"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.