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

Anomaly Detection on Traffic Scene Anomaly Detection (balanced split of 1000 examples)

85Accuracy

Gemini 2.5 Pro

Updated 9d ago

Evaluation Results

Method	Links
Gemini 2.5 Pro 2025.10		85	94	70	80	24.9	938
GPT-5 2025.10		83	88	77	82	28.7	51,851
Gemini 2.5 Flash 2025.10		81	91	69	78	10.6	947
Gemini 1.5 Flash 2025.10		81	90	70	79	2.9	958
Mistral Medium 3 2025.10		81	94	66	78	6.4	1,158
Mistral Medium 3.1 2025.10		80	80	80	80	7.9	1,259
Qwen-VL Max 2025.10		79	87	68	76	7.7	2,193
GPT-4o 2025.10		78	94	60	73	7.4	1,032
Gemini 2.5 Pro Prev 2025.10		77	87	64	74	23.6	898
Gemini 2.0 Thinking 2025.10		75	90	56	69	8.1	937
Gemini 2.5 Flash Prev 2025.10		75	90	56	69	11.2	956
Qwen2.5-VL 72B 2025.10		75	82	64	72	9.4	961
Claude 3.5 Sonnet 2025.10		74	79	66	72	7.3	1,109
Mistral Small 3.1 2025.10		74	71	82	76	11.9	1,057
Gemini 2.0 Flash Exp 2025.10		73	80	62	70	2.6	2,441
GPT-4 Turbo 2025.10		73	96	48	64	7.6	1,055
Claude 3.5 Haiku 2025.10		72	89	50	64	7	1,144
Claude Sonnet 4 2025.10		70	83	50	63	9.8	1,145
Mistral Small 3.2 2025.10		70	78	56	65	5.5	996
Claude Opus 4.1 2025.10		68	95	38	54	19.4	1,238
Pixtral Large 2411 2025.10		67	64	78	70	5.8	1,817
GPT-4.1 Mini 2025.10		66	94	34	50	5.4	1,075
Claude 3.7 Sonnet 2025.10		65	80	40	53	10.8	1,276
GPT-4o Mini 2025.10		65	90	34	49	4.4	14,787
Pixtral 12B 2025.10		64	100	28	44	5.4	1,637
Claude Opus 4 2025.10		62	83	31	45	13.1	1,224
Qwen2.5-VL 32B 2025.10		62	65	53	59	19.9	2,380
Qwen-VL Plus 2025.10		58	90	18	30	2.8	2,155
LLaVA 1.5 7B 2025.10		58	79	22	34	6.7	1,029
GPT-4.1 Nano 2025.10		56	80	16	27	4.3	1,262
Qwen2.5-VL 7B 2025.10		55	55	48	52	4.2	686
Qwen2.5-VL 3B 2025.10		50	50	29	37	3.6	1,489
Gemma3 12B 2025.10		44	46	70	56	9.2	1,254