GSM-Plus-BN - Seed Questions (CoT): leaderboard
GSM-Plus-BN (2026) is a human-verified Bangla translation of the GSM-Plus perturbation benchmark for grade-school math. Accuracy in percent on the unperturbed seed questions with chain-of-thought prompting; higher is better.
Metric: Accuracy (%; unperturbed seed questions; 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 | Overall rank |
|---|---|---|---|
| 1 | GPT-OSS-120B | 92.7 | #700 |
| 2 | Llama 4 Scout Instruct | 90.55 | #1543 |
| 3 | GPT-OSS-20B | 87.8 | #1147 |
| 4 | Qwen 3 32B | 76.25 | #960 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=gsm-plus-bn-seed-questions-cot · How It Works · Data refreshed daily, snapshot 2026-11-13.