BhashaBench - Finance - Hindi: leaderboard
From BharatGen's BhashaBench V1 leaderboard, which scores models on English and Hindi questions sourced from Indian government and domain-specific exams. BhashaBench-Finance tests Indian finance and economics knowledge; this board is accuracy on the Hindi-language questions only (%), higher is better. Flagged runs are skipped.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around December 2027. 31 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-OSS-120B | 64.16 | #346 |
| 2 | DeepSeek V3.1 | 57.04 | #275 |
| 3 | Qwen 3 235B A22B 2507 Instruct | 56.27 | #315 |
| 4 | GPT-4o | 49.82 | #357 |
| 5 | Gemma 2 27B | 41.24 | #803 |
| 6 | Gemma 2 9B | 36.91 | #924 |
| 7 | Gemma 2 27B (IT) | 34.29 | #652 |
| 8 | Pangea-7B | 33.73 | #1223 |
| 9 | GPT-OSS-20B | 32.61 | #523 |
| 10 | Qwen 2.5 3B | 32.13 | #1177 |
| 11 | Gemma 2 9B (IT) | 32.03 | #795 |
| 12 | aya-23-8B | 30.88 | #1267 |
| 13 | Llama 3.1 8B | 30.61 | #1130 |
| 14 | Indic-gemma-7B-finetuned-sft-Navarasa-2.0 | 30.47 | #1372 |
| 15 | Llama 3.1 8B Instruct | 30.27 | #1017 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=bhashabench-finance-hindi · How It Works · Data refreshed daily, snapshot 2026-11-05.