# Rock-Paper-Scissors on Rock-Paper-Scissors (RPS) Source: [Rock-Paper-Scissors on Rock-Paper-Scissors (RPS)]() Collection index: [llms.txt]() Data updated: 2026-06-09T09:13:48.745Z Evaluation of performance in the Rock-Paper-Scissors game, measured using the RPS@5 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 | Rock-Paper-Scissors | | Dataset (including any stated split) | Rock-Paper-Scissors (RPS) | | Metric | RPS@5 Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 26 of 26 | | 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 - [RPS@5 Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | RPS@5 Score | Result date | Report paper | | --- | --- | --- | --- | | Memory w/ MEMOPILOT | 3.28 | Not recorded | 6a279e2890966ade919bf7e5 | | Memory w/ MEMOPILOT | 3.27 | Not recorded | 6a279e2890966ade919bf7e5 | | Memory w/ DeepSeek-V3.2 | 1.64 | Not recorded | 6a279e2890966ade919bf7e5 | | Memory w/ DeepSeek-V3.2 | 1.46 | Not recorded | 6a279e2890966ade919bf7e5 | | Human-Written Counter-Strategy | 1 | Not recorded | 6a279e2890966ade919bf7e5 | | ReasoningBank | 0.81 | Not recorded | 6a279e2890966ade919bf7e5 | | ReasoningBank | 0.81 | Not recorded | 6a279e2890966ade919bf7e5 | | AWM | 0.67 | Not recorded | 6a279e2890966ade919bf7e5 | | AWM | 0.64 | Not recorded | 6a279e2890966ade919bf7e5 | | Reflexion | 0.61 | Not recorded | 6a279e2890966ade919bf7e5 | | Human-Written Counter-Strategy | 0.57 | Not recorded | 6a279e2890966ade919bf7e5 | | Memory w/ Gemini-3.0-Flash | 0.54 | Not recorded | 6a279e2890966ade919bf7e5 | | Reflexion | 0.53 | Not recorded | 6a279e2890966ade919bf7e5 | | MemoryBank | 0.48 | Not recorded | 6a279e2890966ade919bf7e5 | | Memory w/ Gemini-3.0-Flash | 0.45 | Not recorded | 6a279e2890966ade919bf7e5 | | No Memory | 0.44 | Not recorded | 6a279e2890966ade919bf7e5 | | No Memory | 0.43 | Not recorded | 6a279e2890966ade919bf7e5 | | MemoryBank | 0.43 | Not recorded | 6a279e2890966ade919bf7e5 | | Memory w/ Qwen2.5-7B-Instruct | 0.36 | Not recorded | 6a279e2890966ade919bf7e5 | | Memory w/ Qwen2.5-14B-Instruct | 0.34 | Not recorded | 6a279e2890966ade919bf7e5 | | Memory w/ Qwen2.5-14B-Instruct | 0.21 | Not recorded | 6a279e2890966ade919bf7e5 | | Memory w/ Qwen2.5-7B-Instruct | 0.19 | Not recorded | 6a279e2890966ade919bf7e5 | | Full History | 0.03 | Not recorded | 6a279e2890966ade919bf7e5 | | ExpeL | 0.03 | Not recorded | 6a279e2890966ade919bf7e5 | | Full History | 0.02 | Not recorded | 6a279e2890966ade919bf7e5 | | ExpeL | -0.02 | Not recorded | 6a279e2890966ade919bf7e5 | ### Memory w/ MEMOPILOT RPS@5 Score: 3.28. Result ID: 6a27d8dcfbc373592c24d583. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### Memory w/ MEMOPILOT RPS@5 Score: 3.27. Result ID: 6a27d8dcfbc373592c24d584. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### Memory w/ DeepSeek-V3.2 RPS@5 Score: 1.64. Result ID: 6a27d8dcfbc373592c24d57d. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### Memory w/ DeepSeek-V3.2 RPS@5 Score: 1.46. Result ID: 6a27d8dcfbc373592c24d57e. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### Human-Written Counter-Strategy RPS@5 Score: 1. Result ID: 6a27d8dcfbc373592c24d56f. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### ReasoningBank RPS@5 Score: 0.81. Result ID: 6a27d8dcfbc373592c24d579. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### ReasoningBank RPS@5 Score: 0.81. Result ID: 6a27d8dcfbc373592c24d57a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### AWM RPS@5 Score: 0.67. Result ID: 6a27d8dcfbc373592c24d578. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### AWM RPS@5 Score: 0.64. Result ID: 6a27d8dcfbc373592c24d577. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### Reflexion RPS@5 Score: 0.61. Result ID: 6a27d8dcfbc373592c24d571. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### Human-Written Counter-Strategy RPS@5 Score: 0.57. Result ID: 6a27d8dcfbc373592c24d570. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### Memory w/ Gemini-3.0-Flash RPS@5 Score: 0.54. Result ID: 6a27d8dcfbc373592c24d580. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### Reflexion RPS@5 Score: 0.53. Result ID: 6a27d8dcfbc373592c24d572. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### MemoryBank RPS@5 Score: 0.48. Result ID: 6a27d8dcfbc373592c24d576. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### Memory w/ Gemini-3.0-Flash RPS@5 Score: 0.45. Result ID: 6a27d8dcfbc373592c24d57f. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### No Memory RPS@5 Score: 0.44. Result ID: 6a27d8dcfbc373592c24d56c. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### No Memory RPS@5 Score: 0.43. Result ID: 6a27d8dcfbc373592c24d56b. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### MemoryBank RPS@5 Score: 0.43. Result ID: 6a27d8dcfbc373592c24d575. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### Memory w/ Qwen2.5-7B-Instruct RPS@5 Score: 0.36. Result ID: 6a27d8dcfbc373592c24d57b. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### Memory w/ Qwen2.5-14B-Instruct RPS@5 Score: 0.34. Result ID: 6a27d8dcfbc373592c24d582. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### Memory w/ Qwen2.5-14B-Instruct RPS@5 Score: 0.21. Result ID: 6a27d8dcfbc373592c24d581. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### Memory w/ Qwen2.5-7B-Instruct RPS@5 Score: 0.19. Result ID: 6a27d8dcfbc373592c24d57c. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### Full History RPS@5 Score: 0.03. Result ID: 6a27d8dcfbc373592c24d56e. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### ExpeL RPS@5 Score: 0.03. Result ID: 6a27d8dcfbc373592c24d573. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### Full History RPS@5 Score: 0.02. Result ID: 6a27d8dcfbc373592c24d56d. [Reporting paper]() Recorded evaluation configuration: {"Player Model":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### ExpeL RPS@5 Score: -0.02. Result ID: 6a27d8dcfbc373592c24d574. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Player Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.