OpenVLM MMT-Bench - Traffic Anomaly Detection: leaderboard

The "Traffic Anomaly Detection" subtask of OpenVLM MMT-Bench. OpenCompass OpenVLM evaluation of MMT-Bench: multimodal tasks covering visual recognition, localization, OCR, counting, relation reasoning, visual math, and hallucination detection.

Metric: Score (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 207 models tracked.

Top models

#ModelScoreOverall rank
1Gemma 3 12B75#671
2Llama 3.2 90B Vision Instruct70#622
3GPT-4.1 Mini65#355
4GPT-4.1 (2025-04-14)65#250
5Grok 2 (1212)65#496
6Gemma 3 27B60#607
7Gemini 1.5 Flash60#618
8InternVL2-8B55#817
9Qwen 2 VL 2B55#1220
10Claude 3.5 Sonnet55#350
11InternVL3-8B50#620
12InternVL3-38B50#405
13InternVL3-78B50#352
14Gemma 3 4B50#1089
15Llama 3.2 11B Instruct50#1126

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmt-bench-traffic-anomaly-detection · How It Works · Data refreshed daily, snapshot 2026-10-20.