Konkur 1404 - Art — leaderboard
Metric: Accuracy (%, text-only). Source: huggingface.co. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2 0905 | 57.47 |
| 2 | Devstral Small 2 | 55.17 |
| 3 | Qwen 3 VL 235B A22B Instruct | 54.02 |
| 4 | Llama 4 Maverick | 50.57 |
| 5 | Qwen 3 Next 80B A3B Instruct | 50.57 |
| 6 | Llama 3.1 70B Instruct | 49.43 |
| 7 | Gemma 3 27B (IT) | 48.28 |
| 8 | Ministral 3 14B | 43.68 |
| 9 | Gemma 3 4B (IT) | 41.38 |
| 10 | Mixtral 8x22B Instruct | 41.38 |
| 11 | Llama 3.1 8B Instruct | 39.08 |
| 12 | Gemma 3n E4B (IT) | 39.08 |
| 13 | MiMo-V2-Flash | 39.08 |
| 14 | Qwen 3 VL 30B A3B Instruct | 39.08 |
| 15 | Mistral Nemo | 35.63 |
Interactive version: aibenchmarks.dev/benchmark?slug=konkur-1404-art · How the rankings work · Data refreshed daily, snapshot 2026-07-12.