Share your thoughts, 1 month free Claude Pro on usSee more

Food Safety Evaluation on FoodGuardBench

68.16Allergens ASR

LLaMA-3.3-70B

Updated 16d ago

Evaluation Results

Method	Links
LLaMA-3.3-70B 2026.04		68.16	53.1	58.98	66.67	54.09	61.38	56.48	40	55.49
Qwen-2.5-7B 2026.04		62.01	62.08	65.71	73.33	62.12	62.76	65	73.33	62.99
GPT-4o 2026.04		60.89	52.7	56.12	70	52.27	58.28	60.74	66.67	54.84
Mistral-Small4 2026.04		57.54	68.08	67.35	80	69.08	69.31	66.11	46.67	67.58
GLM4-32B 2026.04		56.42	60.88	65.1	46.67	59.55	60.34	61.48	40	60.84
Claude-3.7-Sonnet 2026.04		55.31	31.46	33.27	50	34.09	31.72	42.69	60	34.59
Qwen-3-32B 2026.04		53.31	63.32	62.65	70	58.88	68.62	64.07	66.67	62.76
Qwen-3-8B 2026.04		45.81	65.04	58.78	66.67	57.88	58.97	59.63	53.33	56.38
GPT-4.1 2026.04		41.96	49.73	52.45	60	51.82	49.66	49.81	60	50.54