# Physical Reasoning on Angry Birds Source: [Physical Reasoning on Angry Birds]() Collection index: [llms.txt]() Data updated: 2026-03-17T07:30:03.320Z Evaluation of model performance on the Physical Reasoning task using the Angry Birds 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) | Angry Birds | | 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 | | --- | --- | --- | --- | | Qwen-7B^P&I GRPO | 47.06 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P&I GRPO | 45.61 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P&I SFT | 44.12 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P GRPO | 44.12 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P SFT | 41.18 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P&I SFT | 41.18 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P GRPO | 41.18 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^P SFT | 38.24 | Not recorded | 69b8e0060636e5bf4afbe99b | | Gemini-2.5-Pro | 35.29 | Not recorded | 69b8e0060636e5bf4afbe99b | | GPT-o3 | 35.29 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P&I GRPO | 35.29 | Not recorded | 69b8e0060636e5bf4afbe99b | | Claude 4.0 Opus | 32.35 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P&I SFT | 32.35 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-72B | 29.41 | Not recorded | 69b8e0060636e5bf4afbe99b | | Claude 4.0 Opus | 29.41 | Not recorded | 69b8e0060636e5bf4afbe99b | | Gemini-2.5-Pro | 29.41 | Not recorded | 69b8e0060636e5bf4afbe99b | | GPT-o3 | 29.41 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P GRPO | 29.41 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P&I GRPO | 29.41 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-32B | 26.47 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-72B | 26.47 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P SFT | 26.47 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P&I SFT | 26.47 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P GRPO | 26.47 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^I SFT | 26.47 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^I GRPO | 26.47 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^P SFT | 23.53 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^I SFT | 23.53 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^I GRPO | 23.53 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^I SFT | 23.53 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B^I GRPO | 23.53 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-7B | 20.59 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^I SFT | 20.59 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B^I GRPO | 20.59 | Not recorded | 69b8e0060636e5bf4afbe99b | | MOCK | 17.65 | Not recorded | 69b8e0060636e5bf4afbe99b | | Qwen-3B | 17.65 | Not recorded | 69b8e0060636e5bf4afbe99b | ### Qwen-7B^P&I GRPO Success Rate: 47.06. Result ID: 69b902da47f34ce924a122f8. [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. ### Qwen-7B^P&I GRPO Success Rate: 45.61. Result ID: 69b902da47f34ce924a122f7. [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: 44.12. Result ID: 69b902da47f34ce924a122f2. [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: 44.12. Result ID: 69b902da47f34ce924a122f4. [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. ### Qwen-7B^P SFT Success Rate: 41.18. Result ID: 69b902da47f34ce924a122ee. [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 SFT Success Rate: 41.18. Result ID: 69b902da47f34ce924a122f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^P&I SFT","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-7B^P GRPO Success Rate: 41.18. Result ID: 69b902da47f34ce924a122f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^P GRPO","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-7B^P SFT Success Rate: 38.24. Result ID: 69b902da47f34ce924a122ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^P SFT","World Model":"-"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Success Rate: 35.29. Result ID: 69b902da47f34ce924a122dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Gemini-2.5-Pro","World Model":"-"}. This record does not assert independent reproduction. ### GPT-o3 Success Rate: 35.29. Result ID: 69b902da47f34ce924a122df. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"GPT-o3","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B^P&I GRPO Success Rate: 35.29. Result ID: 69b902da47f34ce924a122ec. [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. ### Claude 4.0 Opus Success Rate: 32.35. Result ID: 69b902da47f34ce924a122db. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Claude 4.0 Opus","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B^P&I SFT Success Rate: 32.35. Result ID: 69b902da47f34ce924a122e6. [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: 29.41. Result ID: 69b902da47f34ce924a122d9. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-72B","World Model":"-"}. This record does not assert independent reproduction. ### Claude 4.0 Opus Success Rate: 29.41. Result ID: 69b902da47f34ce924a122dc. [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: 29.41. Result ID: 69b902da47f34ce924a122de. [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. ### GPT-o3 Success Rate: 29.41. Result ID: 69b902da47f34ce924a122e0. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"GPT-o3","World Model":"GPT-o3"}. This record does not assert independent reproduction. ### Qwen-3B^P GRPO Success Rate: 29.41. Result ID: 69b902da47f34ce924a122e8. [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: 29.41. Result ID: 69b902da47f34ce924a122eb. [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-32B Success Rate: 26.47. Result ID: 69b902da47f34ce924a122d8. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-32B","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-72B Success Rate: 26.47. Result ID: 69b902da47f34ce924a122da. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-72B","World Model":"Qwen-72B"}. This record does not assert independent reproduction. ### Qwen-3B^P SFT Success Rate: 26.47. Result ID: 69b902da47f34ce924a122e2. [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: 26.47. Result ID: 69b902da47f34ce924a122e5. [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-3B^P GRPO Success Rate: 26.47. Result ID: 69b902da47f34ce924a122e7. [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: 26.47. Result ID: 69b902da47f34ce924a122f0. [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-7B^I GRPO Success Rate: 26.47. Result ID: 69b902da47f34ce924a122f6. [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^P SFT Success Rate: 23.53. Result ID: 69b902da47f34ce924a122e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^P SFT","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B^I SFT Success Rate: 23.53. Result ID: 69b902da47f34ce924a122e4. [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-3B^I GRPO Success Rate: 23.53. Result ID: 69b902da47f34ce924a122ea. [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-7B^I SFT Success Rate: 23.53. Result ID: 69b902da47f34ce924a122ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^I SFT","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-7B^I GRPO Success Rate: 23.53. Result ID: 69b902da47f34ce924a122f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B^I GRPO","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-7B Success Rate: 20.59. Result ID: 69b902da47f34ce924a122d7. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-7B","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B^I SFT Success Rate: 20.59. Result ID: 69b902da47f34ce924a122e3. [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: 20.59. Result ID: 69b902da47f34ce924a122e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B^I GRPO","World Model":"-"}. This record does not assert independent reproduction. ### MOCK Success Rate: 17.65. Result ID: 69b902da47f34ce924a122d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy Model":"MOCK","World Model":"-"}. This record does not assert independent reproduction. ### Qwen-3B Success Rate: 17.65. Result ID: 69b902da47f34ce924a122d6. [Reporting paper]() Recorded evaluation configuration: {"Policy Model":"Qwen-3B","World Model":"-"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.