Cedar - Text-Only - English: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around August 2028. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 61.79 |
| 2 | Gemini 2.5 Flash (Thinking) | 57.53 |
| 3 | Kimi K2 | 56.72 |
| 4 | Qwen 3 VL 235B A22B (Thinking) | 55.15 |
| 5 | Gemma 3 27B (IT) | 53.91 |
| 6 | GPT-4o (2024-11-20) | 53.69 |
| 7 | Qwen 3 VL 8B (Thinking) | 49.7 |
| 8 | aya-vision-8B | 45.96 |
| 9 | Llama 3.2 11B Instruct | 43.04 |
| 10 | Pixtral-12B-2409 | 42.37 |
| 11 | Mistral Small 3.2 | 39.97 |
Interactive version: theaggregate.ai/benchmark?slug=cedar-text-only-english · How It Works · Data refreshed daily, snapshot 2026-09-25.