# Reasoning and Knowledge Suite (MMLU, ARC, BoolQ, CSQA, HSwag, PIQA, SocIQ, Wino) Source: [Reasoning and Knowledge Suite (MMLU, ARC, BoolQ, CSQA, HSwag, PIQA, SocIQ, Wino)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:50:01.014Z Evaluation across a broad suite of reasoning and knowledge tasks including MMLU, ARC (Easy/Challenge), BoolQ, CSQA, HSwag, PIQA, SocIQ, and Wino. 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 | Reasoning and Knowledge | | Dataset (including any stated split) | Reasoning and Knowledge Suite (MMLU, ARC-C, ARC-E, BoolQ, CSQA, HSwag, PIQA, SocIQ, Wino) (various) | | Metric | MMLU | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [MMLU](): Higher is better; unit: PERCENT. - [ARC-C](): Higher is better; unit: PERCENT. - [ARC-E](): Higher is better; unit: PERCENT. - [BoolQ](): Higher is better; unit: PERCENT. - [CSQA](): Higher is better; unit: PERCENT. - [HSwag](): Higher is better; unit: PERCENT. - [PIQA](): Higher is better; unit: PERCENT. - [SocIQ](): Higher is better; unit: PERCENT. - [Wino](): Higher is better; unit: PERCENT. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | MMLU | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-4B | 75.78 | Not recorded | 6937ad406cfd488761a4eb25 | | Qwen2.5-3B | 66.86 | Not recorded | 6937ad406cfd488761a4eb25 | | Qwen3-1.7B | 65.35 | Not recorded | 6937ad406cfd488761a4eb25 | | SmolLM3-3B | 63.04 | Not recorded | 6937ad406cfd488761a4eb25 | | Qwen2.5-1.5B | 61.56 | Not recorded | 6937ad406cfd488761a4eb25 | | Llama-3.2-3B | 57.87 | Not recorded | 6937ad406cfd488761a4eb25 | | Qwen2-1.5B | 56.36 | Not recorded | 6937ad406cfd488761a4eb25 | | Gemma2-2B | 55.2 | Not recorded | 6937ad406cfd488761a4eb25 | | Qwen3-0.6B | 55.09 | Not recorded | 6937ad406cfd488761a4eb25 | | PCMind-2.1-Kaiyuan-2B | 53.9 | Not recorded | 6937ad406cfd488761a4eb25 | | SmolLM2-1.7B | 51.99 | Not recorded | 6937ad406cfd488761a4eb25 | | YuLan-Mini-2.4B | 51.76 | Not recorded | 6937ad406cfd488761a4eb25 | | OLMo-2-0425-1B | 44.25 | Not recorded | 6937ad406cfd488761a4eb25 | | Llama-3.2-1B | 37.74 | Not recorded | 6937ad406cfd488761a4eb25 | ### Qwen3-4B MMLU: 75.78. Result ID: 6996c6bf5698665ec4125122. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"4B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### Qwen2.5-3B MMLU: 66.86. Result ID: 6996c6bf5698665ec412511f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"3B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### Qwen3-1.7B MMLU: 65.35. Result ID: 6996c6bf5698665ec4125121. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"1.7B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### SmolLM3-3B MMLU: 63.04. Result ID: 6996c6bf5698665ec4125129. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"3B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### Qwen2.5-1.5B MMLU: 61.56. Result ID: 6996c6bf5698665ec412511e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"1.5B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### Llama-3.2-3B MMLU: 57.87. Result ID: 6996c6bf5698665ec4125125. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"3B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### Qwen2-1.5B MMLU: 56.36. Result ID: 6996c6bf5698665ec412511d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"1.5B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### Gemma2-2B MMLU: 55.2. Result ID: 6996c6bf5698665ec4125123. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"2B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### Qwen3-0.6B MMLU: 55.09. Result ID: 6996c6bf5698665ec4125120. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"0.6B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### PCMind-2.1-Kaiyuan-2B MMLU: 53.9. Result ID: 6996c6bf5698665ec412512a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"2B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### SmolLM2-1.7B MMLU: 51.99. Result ID: 6996c6bf5698665ec4125126. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"1.7B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### YuLan-Mini-2.4B MMLU: 51.76. Result ID: 6996c6bf5698665ec4125128. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"2.4B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### OLMo-2-0425-1B MMLU: 44.25. Result ID: 6996c6bf5698665ec4125127. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"1B","Shot setting":"5 shot"}. This record does not assert independent reproduction. ### Llama-3.2-1B MMLU: 37.74. Result ID: 6996c6bf5698665ec4125124. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"1B","Shot setting":"5 shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.