# Food Safety Evaluation on FoodGuardBench Source: [Food Safety Evaluation on FoodGuardBench]() Collection index: [llms.txt]() Data updated: 2026-04-03T07:24:08.028Z Evaluation of model safety performance specifically concerning food handling and safety standards, measured across various sub-categories like Allergens, Hygiene, Temperature Control, and Contamination. 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 | Safety evaluation against malicious inputs | | Dataset (including any stated split) | FoodGuardBench | | Metric | Allergens ASR | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [Allergens ASR](): Higher is better; unit: PERCENT. - [Contamination ASR](): Higher is better; unit: PERCENT. - [Hygiene ASR](): Higher is better; unit: PERCENT. - [Pest Control ASR](): Higher is better; unit: PERCENT. - [Preparation ASR](): Higher is better; unit: PERCENT. - [Storage ASR](): Higher is better; unit: PERCENT. - [Temperature Control ASR](): Higher is better; unit: PERCENT. - [Water Safety ASR](): Higher is better; unit: PERCENT. - [Overall ASR](): Higher is better; unit: PERCENT. ## Recorded results | Method | Allergens ASR | Result date | Report paper | | --- | --- | --- | --- | | LLaMA-3.3-70B | 68.16 | Not recorded | 69cf496d0636e5bf4afcd900 | | Qwen-2.5-7B | 62.01 | Not recorded | 69cf496d0636e5bf4afcd900 | | GPT-4o | 60.89 | Not recorded | 69cf496d0636e5bf4afcd900 | | Mistral-Small4 | 57.54 | Not recorded | 69cf496d0636e5bf4afcd900 | | GLM4-32B | 56.42 | Not recorded | 69cf496d0636e5bf4afcd900 | | Claude-3.7-Sonnet | 55.31 | Not recorded | 69cf496d0636e5bf4afcd900 | | Qwen-3-32B | 53.31 | Not recorded | 69cf496d0636e5bf4afcd900 | | Qwen-3-8B | 45.81 | Not recorded | 69cf496d0636e5bf4afcd900 | | GPT-4.1 | 41.96 | Not recorded | 69cf496d0636e5bf4afcd900 | ### LLaMA-3.3-70B Allergens ASR: 68.16. Result ID: 69cf6a8847f34ce924b8dba5. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen-2.5-7B Allergens ASR: 62.01. Result ID: 69cf6a8847f34ce924b8dba9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4o Allergens ASR: 60.89. Result ID: 69cf6a8847f34ce924b8dba2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Mistral-Small4 Allergens ASR: 57.54. Result ID: 69cf6a8847f34ce924b8dba6. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GLM4-32B Allergens ASR: 56.42. Result ID: 69cf6a8847f34ce924b8dba4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Claude-3.7-Sonnet Allergens ASR: 55.31. Result ID: 69cf6a8847f34ce924b8dba1. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen-3-32B Allergens ASR: 53.31. Result ID: 69cf6a8847f34ce924b8dba8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen-3-8B Allergens ASR: 45.81. Result ID: 69cf6a8847f34ce924b8dba7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4.1 Allergens ASR: 41.96. Result ID: 69cf6a8847f34ce924b8dba3. [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.