Cedar - Text-Only - Hindi: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around 2029. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash (Thinking) | 51.27 |
| 2 | Qwen 3 VL 235B A22B (Thinking) | 49.06 |
| 3 | GPT-4o (2024-11-20) | 47.45 |
| 4 | Gemma 3 27B (IT) | 46.85 |
| 5 | Kimi K2 | 46.06 |
| 6 | Claude Sonnet 4.5 | 43.95 |
| 7 | aya-vision-8B | 39.56 |
| 8 | Mistral Small 3.2 | 37.26 |
| 9 | Qwen 3 VL 8B (Thinking) | 37.08 |
| 10 | Llama 3.2 11B Instruct | 32.84 |
| 11 | Pixtral-12B-2409 | 30.28 |
Interactive version: theaggregate.ai/benchmark?slug=cedar-text-only-hindi · How It Works · Data refreshed daily, snapshot 2026-09-25.