OpenVLM MME - Text Translation: leaderboard
OpenCompass OpenVLM MME subcategory score for translating text found in images.
Metric: Score. Source: huggingface.co. Saturation forecast: Estimated already saturated. 235 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3-8B | 200 | #620 |
| 2 | Qwen 2 VL 7B | 200 | #750 |
| 3 | Qwen 2 VL 72B | 200 | #460 |
| 4 | InternVL2.5-78B | 200 | #431 |
| 5 | InternVL3-38B | 192.5 | #405 |
| 6 | InternVL3-78B | 192.5 | #352 |
| 7 | InternVL3-14B | 192.5 | #505 |
| 8 | Moonshot v1 8K | 192.5 | #617 |
| 9 | Gemini 2.0 Flash | 185 | #342 |
| 10 | InternVL2-8B | 185 | #817 |
| 11 | GPT-4.1 (2025-04-14) | 185 | #250 |
| 12 | Qwen 2.5 VL 7B | 185 | #643 |
| 13 | MiniCPM-V-2.6 | 177.5 | #836 |
| 14 | Claude 3.7 Sonnet | 177.5 | #249 |
| 15 | Qwen 2 VL 2B | 170 | #1220 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mme-text-translation · How It Works · Data refreshed daily, snapshot 2026-10-20.