Konkur 1404 - Humanities — leaderboard
Metric: Accuracy (%, text-only). Source: huggingface.co. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 235B A22B Instruct | 52.15 |
| 2 | Qwen 3 Next 80B A3B Instruct | 46.24 |
| 3 | Devstral Small 2 | 45.7 |
| 4 | Kimi K2 0905 | 45.16 |
| 5 | Llama 4 Maverick | 43.55 |
| 6 | Llama 3.1 70B Instruct | 43.01 |
| 7 | MiMo-V2-Flash | 42.47 |
| 8 | Qwen 3 VL 30B A3B Instruct | 41.4 |
| 9 | Gemma 3 27B (IT) | 40.32 |
| 10 | Ministral 3 14B | 38.17 |
| 11 | Gemma 3 12B (IT) | 37.5 |
| 12 | Mixtral 8x22B Instruct | 37.1 |
| 13 | Gemma 3n E4B (IT) | 35.48 |
| 14 | command-r7B-12-2024 | 32.8 |
| 15 | Gemma 3 4B (IT) | 30.65 |
Interactive version: aibenchmarks.dev/benchmark?slug=konkur-1404-humanities · How the rankings work · Data refreshed daily, snapshot 2026-07-12.