OpenVLM MMT-Bench - Astronomical Recognition: leaderboard
The "Astronomical Recognition" 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 | GPT-4.1 (2025-04-14) | 100 | #250 |
| 2 | Claude 3.7 Sonnet | 100 | #249 |
| 3 | Gemini 1.5 Pro | 100 | #445 |
| 4 | Claude 3.5 Sonnet | 100 | #350 |
| 5 | Qwen 2 VL 2B | 88.9 | #1220 |
| 6 | Llama 3.2 11B Instruct | 88.9 | #1126 |
| 7 | Grok 2 (1212) | 88.9 | #496 |
| 8 | Llama 3.2 90B Vision Instruct | 88.9 | #622 |
| 9 | Claude 3 Haiku | 88.9 | #803 |
| 10 | GPT-4.1 Mini | 77.8 | #355 |
| 11 | Gemma 3 27B | 77.8 | #607 |
| 12 | Gemma 3 12B | 77.8 | #671 |
| 13 | Gemini 1.5 Flash | 77.8 | #618 |
| 14 | GPT-4.1 Nano | 66.7 | #731 |
| 15 | InternVL3-78B | 66.7 | #352 |
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-astronomical-recognition · How It Works · Data refreshed daily, snapshot 2026-10-20.