Anomaly Detection on Traffic Scene Anomaly Detection (balanced split of 1000 examples) benchmark leaderboard · SOTA2 Research

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

85AccuracyGemini 2.5 Pro

Evaluation Results

Method	Links
Gemini 2.5 Pro2025.10		85	94	70	80	24.9	938
GPT-52025.10		83	88	77	82	28.7	51,851
Gemini 2.5 Flash2025.10		81	91	69	78	10.6	947
Gemini 1.5 Flash2025.10		81	90	70	79	2.9	958
Mistral Medium 32025.10		81	94	66	78	6.4	1,158
Mistral Medium 3.12025.10		80	80	80	80	7.9	1,259
Qwen-VL Max2025.10		79	87	68	76	7.7	2,193
GPT-4o2025.10		78	94	60	73	7.4	1,032
Gemini 2.5 Pro Prev2025.10		77	87	64	74	23.6	898
Gemini 2.0 Thinking2025.10		75	90	56	69	8.1	937
Gemini 2.5 Flash Prev2025.10		75	90	56	69	11.2	956
Qwen2.5-VL 72B2025.10		75	82	64	72	9.4	961
Claude 3.5 Sonnet2025.10		74	79	66	72	7.3	1,109
Mistral Small 3.12025.10		74	71	82	76	11.9	1,057
Gemini 2.0 Flash Exp2025.10		73	80	62	70	2.6	2,441
GPT-4 Turbo2025.10		73	96	48	64	7.6	1,055
Claude 3.5 Haiku2025.10		72	89	50	64	7	1,144
Claude Sonnet 42025.10		70	83	50	63	9.8	1,145
Mistral Small 3.22025.10		70	78	56	65	5.5	996
Claude Opus 4.12025.10		68	95	38	54	19.4	1,238
Pixtral Large 24112025.10		67	64	78	70	5.8	1,817
GPT-4.1 Mini2025.10		66	94	34	50	5.4	1,075
Claude 3.7 Sonnet2025.10		65	80	40	53	10.8	1,276
GPT-4o Mini2025.10		65	90	34	49	4.4	14,787
Pixtral 12B2025.10		64	100	28	44	5.4	1,637
Claude Opus 42025.10		62	83	31	45	13.1	1,224
Qwen2.5-VL 32B2025.10		62	65	53	59	19.9	2,380
Qwen-VL Plus2025.10		58	90	18	30	2.8	2,155
LLaVA 1.5 7B2025.10		58	79	22	34	6.7	1,029
GPT-4.1 Nano2025.10		56	80	16	27	4.3	1,262
Qwen2.5-VL 7B2025.10		55	55	48	52	4.2	686
Qwen2.5-VL 3B2025.10		50	50	29	37	3.6	1,489
Gemma3 12B2025.10		44	46	70	56	9.2	1,254