# Language Understanding on ITALIC Source: [Language Understanding on ITALIC]() Collection index: [llms.txt]() Data updated: 2026-05-11T10:11:10.034Z Evaluation of model performance on the ITALIC dataset for general Language Understanding tasks, measured using 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 | Language Understanding | | Dataset (including any stated split) | ITALIC | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 | | --- | --- | --- | --- | | GPT-5 nano | 86.6 | Not recorded | 6a0162badbc836b87d82332a | | Ministral-3-8B | 82.5 | Not recorded | 6a0162badbc836b87d82332a | | gemma-3-12b-it | 77.1 | Not recorded | 6a0162badbc836b87d82332a | | Qwen3-8B | 73 | Not recorded | 6a0162badbc836b87d82332a | | Llama-3.1-8B | 68.3 | Not recorded | 6a0162badbc836b87d82332a | | Qwen3-4B | 67.8 | Not recorded | 6a0162badbc836b87d82332a | | Velvet-14B | 66.6 | Not recorded | 6a0162badbc836b87d82332a | | gemma-3-4b-it | 63.4 | Not recorded | 6a0162badbc836b87d82332a | | LLaMAntino-3-8B | 62.5 | Not recorded | 6a0162badbc836b87d82332a | | EngGPT2-16B-A3B | 60.9 | Not recorded | 6a0162badbc836b87d82332a | | gpt-oss-20b | 58.9 | Not recorded | 6a0162badbc836b87d82332a | | Moonlight-16B-A3B | 58.2 | Not recorded | 6a0162badbc836b87d82332a | | Llama-3.2-3B | 55.7 | Not recorded | 6a0162badbc836b87d82332a | | deepseek-moe-16b | 46.6 | Not recorded | 6a0162badbc836b87d82332a | | FastwebMIIA-7B | 43.7 | Not recorded | 6a0162badbc836b87d82332a | | Minerva-7B | 40.6 | Not recorded | 6a0162badbc836b87d82332a | ### GPT-5 nano Accuracy: 86.6. Result ID: 6a01ab3c47f34ce924e41fa1. [Reporting paper]() Recorded evaluation configuration: {"Scale":"nano"}. This record does not assert independent reproduction. ### Ministral-3-8B Accuracy: 82.5. Result ID: 6a01ab3c47f34ce924e41fa0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### gemma-3-12b-it Accuracy: 77.1. Result ID: 6a01ab3c47f34ce924e41f9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"12B"}. This record does not assert independent reproduction. ### Qwen3-8B Accuracy: 73. Result ID: 6a01ab3c47f34ce924e41f9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### Llama-3.1-8B Accuracy: 68.3. Result ID: 6a01ab3c47f34ce924e41f9d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### Qwen3-4B Accuracy: 67.8. Result ID: 6a01ab3c47f34ce924e41f9a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### Velvet-14B Accuracy: 66.6. Result ID: 6a01ab3c47f34ce924e41f98. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"14B"}. This record does not assert independent reproduction. ### gemma-3-4b-it Accuracy: 63.4. Result ID: 6a01ab3c47f34ce924e41f9e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### LLaMAntino-3-8B Accuracy: 62.5. Result ID: 6a01ab3c47f34ce924e41f99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### EngGPT2-16B-A3B Accuracy: 60.9. Result ID: 6a01ab3c47f34ce924e41f95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"16B"}. This record does not assert independent reproduction. ### gpt-oss-20b Accuracy: 58.9. Result ID: 6a01ab3c47f34ce924e41fa3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"20B"}. This record does not assert independent reproduction. ### Moonlight-16B-A3B Accuracy: 58.2. Result ID: 6a01ab3c47f34ce924e41fa4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"16B"}. This record does not assert independent reproduction. ### Llama-3.2-3B Accuracy: 55.7. Result ID: 6a01ab3c47f34ce924e41f9c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"3B"}. This record does not assert independent reproduction. ### deepseek-moe-16b Accuracy: 46.6. Result ID: 6a01ab3c47f34ce924e41fa2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"16B"}. This record does not assert independent reproduction. ### FastwebMIIA-7B Accuracy: 43.7. Result ID: 6a01ab3c47f34ce924e41f96. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### Minerva-7B Accuracy: 40.6. Result ID: 6a01ab3c47f34ce924e41f97. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.