# Question Answering on ARC (Average rank) Source: [Question Answering on ARC (Average rank)]() Collection index: [llms.txt]() Data updated: 2026-05-11T10:11:09.722Z Evaluation of model performance on the Abstract Reasoning Corpus (ARC) for Question Answering, measured using the Average rank 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 | Question Answering | | Dataset (including any stated split) | ARC | | Metric | Average Rank | | Unit | SCALAR | | Direction | Lower 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 - [Average Rank](): Lower is better; unit: SCALAR. ## Recorded results | Method | Average Rank | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-8B | 1.7 | Not recorded | 6a0162badbc836b87d82332a | | GPT-5 nano | 2 | Not recorded | 6a0162badbc836b87d82332a | | gpt-oss-20b | 3 | Not recorded | 6a0162badbc836b87d82332a | | Ministral-3-8B | 4 | Not recorded | 6a0162badbc836b87d82332a | | gemma-3-12b-it | 5 | Not recorded | 6a0162badbc836b87d82332a | | Qwen3-4B | 5.3 | Not recorded | 6a0162badbc836b87d82332a | | EngGPT2-16B-A3B | 8.3 | Not recorded | 6a0162badbc836b87d82332a | | Llama-3.1-8B | 8.3 | Not recorded | 6a0162badbc836b87d82332a | | gemma-3-4b-it | 9.3 | Not recorded | 6a0162badbc836b87d82332a | | Moonlight-16B-A3B | 9.7 | Not recorded | 6a0162badbc836b87d82332a | | LLaMAntino-3-8B | 10.7 | Not recorded | 6a0162badbc836b87d82332a | | Velvet-14B | 11.7 | Not recorded | 6a0162badbc836b87d82332a | | Llama-3.2-3B | 12 | Not recorded | 6a0162badbc836b87d82332a | | FastwebMIIA-7B | 14 | Not recorded | 6a0162badbc836b87d82332a | | deepseek-moe-16b | 15 | Not recorded | 6a0162badbc836b87d82332a | | Minerva-7B | 16 | Not recorded | 6a0162badbc836b87d82332a | ### Qwen3-8B Average Rank: 1.7. Result ID: 6a01ab3c47f34ce924e41ecb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### GPT-5 nano Average Rank: 2. Result ID: 6a01ab3c47f34ce924e41ed1. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### gpt-oss-20b Average Rank: 3. Result ID: 6a01ab3c47f34ce924e41ed3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"20B"}. This record does not assert independent reproduction. ### Ministral-3-8B Average Rank: 4. Result ID: 6a01ab3c47f34ce924e41ed0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### gemma-3-12b-it Average Rank: 5. Result ID: 6a01ab3c47f34ce924e41ecf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"12B","Instruction Tuned":"true"}. This record does not assert independent reproduction. ### Qwen3-4B Average Rank: 5.3. Result ID: 6a01ab3c47f34ce924e41eca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### EngGPT2-16B-A3B Average Rank: 8.3. Result ID: 6a01ab3c47f34ce924e41ec5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"16B"}. This record does not assert independent reproduction. ### Llama-3.1-8B Average Rank: 8.3. Result ID: 6a01ab3c47f34ce924e41ecd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### gemma-3-4b-it Average Rank: 9.3. Result ID: 6a01ab3c47f34ce924e41ece. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"4B","Instruction Tuned":"true"}. This record does not assert independent reproduction. ### Moonlight-16B-A3B Average Rank: 9.7. Result ID: 6a01ab3c47f34ce924e41ed4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"16B"}. This record does not assert independent reproduction. ### LLaMAntino-3-8B Average Rank: 10.7. Result ID: 6a01ab3c47f34ce924e41ec9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### Velvet-14B Average Rank: 11.7. Result ID: 6a01ab3c47f34ce924e41ec8. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"14B"}. This record does not assert independent reproduction. ### Llama-3.2-3B Average Rank: 12. Result ID: 6a01ab3c47f34ce924e41ecc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"3B"}. This record does not assert independent reproduction. ### FastwebMIIA-7B Average Rank: 14. Result ID: 6a01ab3c47f34ce924e41ec6. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction. ### deepseek-moe-16b Average Rank: 15. Result ID: 6a01ab3c47f34ce924e41ed2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"16B"}. This record does not assert independent reproduction. ### Minerva-7B Average Rank: 16. Result ID: 6a01ab3c47f34ce924e41ec7. [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.