Cedar - Text-Only - Spanish: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around 2029. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash (Thinking) | 52.98 |
| 2 | Qwen 3 VL 235B A22B (Thinking) | 52.88 |
| 3 | Kimi K2 | 49.87 |
| 4 | Gemma 3 27B (IT) | 48.8 |
| 5 | GPT-4o (2024-11-20) | 44.55 |
| 6 | Qwen 3 VL 8B (Thinking) | 42.25 |
| 7 | aya-vision-8B | 40.37 |
| 8 | Pixtral-12B-2409 | 37.27 |
| 9 | Claude Sonnet 4.5 | 33.59 |
| 10 | Mistral Small 3.2 | 28.75 |
| 11 | Llama 3.2 11B Instruct | 21.86 |
Interactive version: theaggregate.ai/benchmark?slug=cedar-text-only-spanish · How It Works · Data refreshed daily, snapshot 2026-09-25.