# Physical Reasoning on Cut the Rope Source: [Physical Reasoning on Cut the Rope]() Collection index: [llms.txt]() Data updated: 2026-03-17T07:30:03.346Z Evaluation of model performance on the Physical Reasoning task using the Cut the Rope dataset, measured by Success Rate. 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 | Physical Reasoning | | Dataset (including any stated split) | Cut the Rope | | Metric | Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 36 of 36 | | 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 - [Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Success Rate | Result date | Report paper | | --- | --- | --- | --- | | Claude 4.0 Opus | 26.14 | Not recorded | 69b8e0060636e5bf4afbe99b | | Claude 4.0 Opus | 23.86 | Not recorded | 69b8e0060636e5bf4afbe99b | | Gemini-2.5-Pro | 22.73 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P&I GRPO | 21.2 | Not recorded | 69b8e0060636e5bf4afbe99b | | Gemini-2.5-Pro | 20.45 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P&I SFT | 19.33 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P GRPO | 18.88 | Not recorded | 69b8e0060636e5bf4afbe99b | | GPT-o3 | 18.18 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P SFT | 17.5 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P&I GRPO | 17.05 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P&I SFT | 16.55 | Not recorded | 69b8e0060636e5bf4afbe99b | | GPT-o3 | 16.5 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P GRPO | 16.1 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P&I GRPO | 15.8 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P SFT | 15.35 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P&I SFT | 14.05 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-72B | 13.64 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P GRPO | 12.98 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P&I GRPO | 12.1 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P SFT | 11.85 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P&I SFT | 11.6 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-72B | 11.5 | Not recorded | 69b8e0060636e5bf4afbe99b | | MOCK | 11.36 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P GRPO | 11.05 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^I SFT | 10.36 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P SFT | 10.23 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^I GRPO | 10.15 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^I GRPO | 9.88 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^I SFT | 9.13 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B | 9.09 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^I SFT | 8.21 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B | 7.95 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^I GRPO | 7.95 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^I SFT | 7.8 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^I GRPO | 7.75 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-32B | 6.82 | Not recorded | 69b8e0060636e5bf4afbe99b | ### Claude 4.0 Opus Success Rate: 26.14. Result ID: 69b902da47f34ce924a122ff. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Claude 4.0 Opus","World Model":"-"}. This record does not assert independent reproduction. ### Claude 4.0 Opus Success Rate: 23.86. Result ID: 69b902da47f34ce924a12300. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Claude 4.0 Opus","World Model":"Claude 4.0 Opus"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Success Rate: 22.73. Result ID: 69b902da47f34ce924a12301. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Gemini-2.5-Pro","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-7B^P&I GRPO Success Rate: 21.2. Result ID: 69b902da47f34ce924a1231c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^P&I GRPO","World Model":"Qwen-7B^P&I"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Success Rate: 20.45. Result ID: 69b902da47f34ce924a12302. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Gemini-2.5-Pro","World Model":"Gemini-2.5-Pro"}. This record does not assert independent reproduction. ### Qwen-7B^P&I SFT Success Rate: 19.33. Result ID: 69b902da47f34ce924a12316. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^P&I SFT","World Model":"Qwen-7B^P&I"}. This record does not assert independent reproduction. ### Qwen-7B^P GRPO Success Rate: 18.88. Result ID: 69b902da47f34ce924a12318. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^P GRPO","World Model":"Qwen-7B^P"}. This record does not assert independent reproduction. ### GPT-o3 Success Rate: 18.18. Result ID: 69b902da47f34ce924a12303. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"GPT-o3","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-7B^P SFT Success Rate: 17.5. Result ID: 69b902da47f34ce924a12312. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^P SFT","World Model":"Qwen-7B^P"}. This record does not assert independent reproduction. ### Qwen-7B^P&I GRPO Success Rate: 17.05. Result ID: 69b902da47f34ce924a1231b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^P&I GRPO","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-7B^P&I SFT Success Rate: 16.55. Result ID: 69b902da47f34ce924a12315. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^P&I SFT","World Model":"-"}. This record does not assert independent reproduction. ### GPT-o3 Success Rate: 16.5. Result ID: 69b902da47f34ce924a12304. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"GPT-o3","World Model":"GPT-o3"}. This record does not assert independent reproduction. ### Qwen-7B^P GRPO Success Rate: 16.1. Result ID: 69b902da47f34ce924a12317. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^P GRPO","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B^P&I GRPO Success Rate: 15.8. Result ID: 69b902da47f34ce924a12310. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^P&I GRPO","World Model":"Qwen-3B^P&I"}. This record does not assert independent reproduction. ### Qwen-7B^P SFT Success Rate: 15.35. Result ID: 69b902da47f34ce924a12311. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^P SFT","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B^P&I SFT Success Rate: 14.05. Result ID: 69b902da47f34ce924a1230a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^P&I SFT","World Model":"Qwen-3B^P&I"}. This record does not assert independent reproduction. ### Qwen-72B Success Rate: 13.64. Result ID: 69b902da47f34ce924a122fd. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-72B","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B^P GRPO Success Rate: 12.98. Result ID: 69b902da47f34ce924a1230c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^P GRPO","World Model":"Qwen-3B^P"}. This record does not assert independent reproduction. ### Qwen-3B^P&I GRPO Success Rate: 12.1. Result ID: 69b902da47f34ce924a1230f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^P&I GRPO","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B^P SFT Success Rate: 11.85. Result ID: 69b902da47f34ce924a12306. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^P SFT","World Model":"Qwen-3B^P"}. This record does not assert independent reproduction. ### Qwen-3B^P&I SFT Success Rate: 11.6. Result ID: 69b902da47f34ce924a12309. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^P&I SFT","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-72B Success Rate: 11.5. Result ID: 69b902da47f34ce924a122fe. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-72B","World Model":"Qwen-72B"}. This record does not assert independent reproduction. ### MOCK Success Rate: 11.36. Result ID: 69b902da47f34ce924a122f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"MOCK","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B^P GRPO Success Rate: 11.05. Result ID: 69b902da47f34ce924a1230b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^P GRPO","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-7B^I SFT Success Rate: 10.36. Result ID: 69b902da47f34ce924a12314. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^I SFT","World Model":"Qwen-7B^I"}. This record does not assert independent reproduction. ### Qwen-3B^P SFT Success Rate: 10.23. Result ID: 69b902da47f34ce924a12305. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^P SFT","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-7B^I GRPO Success Rate: 10.15. Result ID: 69b902da47f34ce924a1231a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^I GRPO","World Model":"Qwen-7B^I"}. This record does not assert independent reproduction. ### Qwen-3B^I GRPO Success Rate: 9.88. Result ID: 69b902da47f34ce924a1230e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^I GRPO","World Model":"Qwen-3B^I"}. This record does not assert independent reproduction. ### Qwen-3B^I SFT Success Rate: 9.13. Result ID: 69b902da47f34ce924a12308. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^I SFT","World Model":"Qwen-3B^I"}. This record does not assert independent reproduction. ### Qwen-7B Success Rate: 9.09. Result ID: 69b902da47f34ce924a122fb. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-7B^I SFT Success Rate: 8.21. Result ID: 69b902da47f34ce924a12313. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^I SFT","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B Success Rate: 7.95. Result ID: 69b902da47f34ce924a122fa. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-7B^I GRPO Success Rate: 7.95. Result ID: 69b902da47f34ce924a12319. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^I GRPO","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B^I SFT Success Rate: 7.8. Result ID: 69b902da47f34ce924a12307. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^I SFT","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B^I GRPO Success Rate: 7.75. Result ID: 69b902da47f34ce924a1230d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^I GRPO","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-32B Success Rate: 6.82. Result ID: 69b902da47f34ce924a122fc. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-32B","World Model":"-"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.