# Common Sense Reasoning on WorldSense Source: [Common Sense Reasoning on WorldSense]() Collection index: [llms.txt]() Data updated: 2026-05-22T08:06:13.527Z Evaluation of model performance on the WorldSense dataset for common sense reasoning tasks, measured by accuracy. 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 | Common Sense Reasoning | | Dataset (including any stated split) | WorldSense | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Gemini-2.5-Pro | 64.6 | Not recorded | 6a0fe328f984739ed6739ea8 | | Gemini-2.0-Flash | 56.2 | Not recorded | 6a0fe328f984739ed6739ea8 | | LatentOmni | 48.9 | Not recorded | 6a0fe328f984739ed6739ea8 | | OmniVinci | 48.2 | Not recorded | 6a0fe328f984739ed6739ea8 | | Qwen2.5-Omni-7B + Vanilla SFT | 47.5 | Not recorded | 6a0fe328f984739ed6739ea8 | | HumanOmniV2-7B | 47.1 | Not recorded | 6a0fe328f984739ed6739ea8 | | Qwen2.5-Omni-7B + Explicit Text CoT | 46.6 | Not recorded | 6a0fe328f984739ed6739ea8 | | Qwen2.5-Omni-7B | 45.4 | Not recorded | 6a0fe328f984739ed6739ea8 | | Baichuan-Omni-1.5 | 43.3 | Not recorded | 6a0fe328f984739ed6739ea8 | | GPT-4o | 42.6 | Not recorded | 6a0fe328f984739ed6739ea8 | | VITA-1.5-7B | 36.9 | Not recorded | 6a0fe328f984739ed6739ea8 | | MiniCPM-o-7B | 29.7 | Not recorded | 6a0fe328f984739ed6739ea8 | | VideoLLaMA2-7B | 25.4 | Not recorded | 6a0fe328f984739ed6739ea8 | | Llama 3 405B | 0.637 | Not recorded | 68fa75d11e209131cea6a028 | | Llama 3 70B | 0.611 | Not recorded | 68fa75d11e209131cea6a028 | | Mixtral 8x22B | 0.515 | Not recorded | 68fa75d11e209131cea6a028 | | Gemma 7B | 0.46 | Not recorded | 68fa75d11e209131cea6a028 | | Llama 3 8B | 0.455 | Not recorded | 68fa75d11e209131cea6a028 | | Mistral 7B | 0.449 | Not recorded | 68fa75d11e209131cea6a028 | ### Gemini-2.5-Pro Accuracy: 64.6. Result ID: 6a100e71fbc373592c08dadf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Accessibility":"Proprietary"}. This record does not assert independent reproduction. ### Gemini-2.0-Flash Accuracy: 56.2. Result ID: 6a100e71fbc373592c08dade. [Reporting paper]() Recorded evaluation configuration: {"Model Accessibility":"Proprietary"}. This record does not assert independent reproduction. ### LatentOmni Accuracy: 48.9. Result ID: 6a100e71fbc373592c08dadc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Accessibility":"Open-source","Training/Reasoning Strategy":"Latent reasoning"}. This record does not assert independent reproduction. ### OmniVinci Accuracy: 48.2. Result ID: 6a100e71fbc373592c08dad8. [Reporting paper]() Recorded evaluation configuration: {"Model Accessibility":"Open-source"}. This record does not assert independent reproduction. ### Qwen2.5-Omni-7B + Vanilla SFT Accuracy: 47.5. Result ID: 6a100e71fbc373592c08dadb. [Reporting paper]() Recorded evaluation configuration: {"Model Accessibility":"Open-source","Training/Reasoning Strategy":"Vanilla SFT"}. This record does not assert independent reproduction. ### HumanOmniV2-7B Accuracy: 47.1. Result ID: 6a100e71fbc373592c08dad6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Accessibility":"Open-source"}. This record does not assert independent reproduction. ### Qwen2.5-Omni-7B + Explicit Text CoT Accuracy: 46.6. Result ID: 6a100e71fbc373592c08dada. [Reporting paper]() Recorded evaluation configuration: {"Model Accessibility":"Open-source","Training/Reasoning Strategy":"Explicit Text CoT"}. This record does not assert independent reproduction. ### Qwen2.5-Omni-7B Accuracy: 45.4. Result ID: 6a100e71fbc373592c08dad9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Accessibility":"Open-source","Training/Reasoning Strategy":"Base"}. This record does not assert independent reproduction. ### Baichuan-Omni-1.5 Accuracy: 43.3. Result ID: 6a100e71fbc373592c08dad7. [Reporting paper]() Recorded evaluation configuration: {"Model Accessibility":"Open-source"}. This record does not assert independent reproduction. ### GPT-4o Accuracy: 42.6. Result ID: 6a100e71fbc373592c08dadd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Accessibility":"Proprietary"}. This record does not assert independent reproduction. ### VITA-1.5-7B Accuracy: 36.9. Result ID: 6a100e71fbc373592c08dad5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Accessibility":"Open-source"}. This record does not assert independent reproduction. ### MiniCPM-o-7B Accuracy: 29.7. Result ID: 6a100e71fbc373592c08dad4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Accessibility":"Open-source"}. This record does not assert independent reproduction. ### VideoLLaMA2-7B Accuracy: 25.4. Result ID: 6a100e71fbc373592c08dad3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Accessibility":"Open-source"}. This record does not assert independent reproduction. ### Llama 3 405B Accuracy: 0.637. Result ID: 6993ff653a6c3148491a2d1c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Llama 3 70B Accuracy: 0.611. Result ID: 6993ff653a6c3148491a2d1a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Mixtral 8x22B Accuracy: 0.515. Result ID: 6993ff653a6c3148491a2d1b. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemma 7B Accuracy: 0.46. Result ID: 6993ff653a6c3148491a2d19. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Llama 3 8B Accuracy: 0.455. Result ID: 6993ff653a6c3148491a2d17. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Mistral 7B Accuracy: 0.449. Result ID: 6993ff653a6c3148491a2d18. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.