OpenVLM MMT-Bench - KD: leaderboard
The "KD" 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 | InternVL3-78B | 77.8 | #352 |
| 2 | Grok 2 (1212) | 76 | #496 |
| 3 | InternVL3-38B | 74.8 | #405 |
| 4 | Qwen 2 VL 72B | 74 | #460 |
| 5 | InternVL3-14B | 71 | #505 |
| 6 | GPT-4.1 (2025-04-14) | 66.6 | #250 |
| 7 | GPT-4.1 Nano | 60.3 | #731 |
| 8 | InternVL3-8B | 58.1 | #620 |
| 9 | Gemma 3 27B | 57.3 | #607 |
| 10 | Pixtral-12B | 55.3 | #808 |
| 11 | Qwen 2 VL 7B | 52.8 | #750 |
| 12 | Gemini 1.5 Pro | 52.1 | #445 |
| 13 | InternVL2-8B | 51.1 | #817 |
| 14 | Claude 3 Haiku | 49.1 | #803 |
| 15 | GPT-4.1 Mini | 46.3 | #355 |
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-kd · How It Works · Data refreshed daily, snapshot 2026-10-20.