BanglaMedVQA (CoT): leaderboard
Metric: Exact-match accuracy (%; mean of the Chest X-Ray and MedICaT subsets, 1,000 questions each; Bangla questions, chain-of-thought prompt; exact match with the reference answer). Source: arxiv.org. Saturation forecast: Around 2033. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 3 12B | 35.75 |
| 2 | Gemini 2.5 Flash | 32.5 |
| 3 | Qwen 2.5 VL 7B Instruct | 24.5 |
| 4 | GPT-4.1 Mini | 13.75 |
Interactive version: theaggregate.ai/benchmark?slug=banglamedvqa-cot · How It Works · Data refreshed daily, snapshot 2026-09-26.