GSM-Plus-BN - Problem Understanding (CoT): leaderboard
Metric: Accuracy (%; problem understanding perturbation, the problem reworded; Bangla grade-school math word problems translated from GSM-Plus and verified by human translators; chain-of-thought prompting; Groq API). Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-OSS-120B | 91.82 |
| 2 | Llama 4 Scout Instruct | 88.82 |
| 3 | GPT-OSS-20B | 86.63 |
| 4 | Qwen 3 32B | 77.05 |
Interactive version: theaggregate.ai/benchmark?slug=gsm-plus-bn-problem-understanding-cot · How It Works · Data refreshed daily, snapshot 2026-09-29.