OpenVLM MMT-Bench - Helmet Anomaly Detection: leaderboard
The "Helmet 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3-38B | 90 | #405 |
| 2 | InternVL3-78B | 90 | #352 |
| 3 | GPT-4.1 (2025-04-14) | 90 | #250 |
| 4 | Gemma 3 27B | 90 | #607 |
| 5 | Llama 3.2 11B Instruct | 90 | #1126 |
| 6 | InternVL3-8B | 85 | #620 |
| 7 | InternVL3-14B | 85 | #505 |
| 8 | Gemma 3 4B | 85 | #1089 |
| 9 | Llama 3.2 90B Vision Instruct | 85 | #622 |
| 10 | Claude 3.7 Sonnet | 80 | #249 |
| 11 | Gemini 1.5 Pro | 80 | #445 |
| 12 | Gemma 3 12B | 80 | #671 |
| 13 | Gemini 1.5 Flash | 80 | #618 |
| 14 | Grok 2 (1212) | 80 | #496 |
| 15 | Moonshot v1 8K | 80 | #617 |
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-helmet-anomaly-detection · How It Works · Data refreshed daily, snapshot 2026-10-20.