Konkur 1404 - Foreign Language — leaderboard

Metric: Accuracy (%, text-only). Source: huggingface.co. 18 models tracked.

Top models

#ModelScore
1Ministral 3 14B44.23
2Kimi K2 090540.38
3Qwen 3 VL 235B A22B Instruct40.38
4Gemma 3 27B (IT)39.42
5Gemma 3 4B (IT)38.46
6Llama 3.1 70B Instruct37.5
7Qwen 3 Next 80B A3B Instruct37.5
8Devstral Small 237.5
9Qwen 3 VL 30B A3B Instruct37.5
10Llama 4 Maverick36.54
11Mistral Nemo35.58
12Gemma 3n E4B (IT)34.62
13Mixtral 8x22B Instruct34.62
14Ministral 8B34.62
15command-r7B-12-202430.77

Interactive version: aibenchmarks.dev/benchmark?slug=konkur-1404-foreign-language · How the rankings work · Data refreshed daily, snapshot 2026-07-12.