Konkur 1404 - Mathematics — leaderboard
Metric: Accuracy (%, text-only). Source: huggingface.co. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 235B A22B Instruct | 60 |
| 2 | Kimi K2 0905 | 52.17 |
| 3 | Qwen 3 Next 80B A3B Instruct | 47.83 |
| 4 | Qwen 3 VL 30B A3B Instruct | 46.96 |
| 5 | Gemma 3 27B (IT) | 44.35 |
| 6 | Devstral Small 2 | 44.35 |
| 7 | Llama 3.1 70B Instruct | 42.61 |
| 8 | MiMo-V2-Flash | 40 |
| 9 | Ministral 3 14B | 35.65 |
| 10 | Gemma 3n E4B (IT) | 34.78 |
| 11 | Ministral 8B | 33.91 |
| 12 | Mixtral 8x22B Instruct | 33.04 |
| 13 | Mistral Nemo | 31.3 |
| 14 | Llama 4 Maverick | 30.43 |
| 15 | Gemma 3 4B (IT) | 29.57 |
Interactive version: aibenchmarks.dev/benchmark?slug=konkur-1404-mathematics · How the rankings work · Data refreshed daily, snapshot 2026-07-12.