Kaggle MultiLoKo - Korean Task v7: leaderboard

Native model scores in the source’s stated configuration. Metric: Exact Match (%). Source: https://www.kaggle.com/benchmarks/metaresearch/multiloko

Metric: Exact Match (%). Source: www.kaggle.com. Saturation forecast: Around January 2028. 16 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-6.1 Sol57.2#12
2GPT-6 Astra56#8
3Gemini 3.1 Pro (Preview)55.2#99
4GPT-6 Luna48#105
5Gemini 3.8 Flash46.8#39
6Qwen 3.8 Max43.2#64
7Grok 4.741.6#48
8Gemini 4 Argon35.2#14
9GLM-524.8#267
10Claude Opus 5.523.2#7
11Claude Sonnet 5.519.2#21
12Gemma 4 31B18.4#385
13Kimi K313.2#59
14Claude Sonnet 512.8#118
15GLM-5.3 Flash10.4#136

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=kaggle-multiloko-korean-task-v7 · How It Works · Data refreshed daily, snapshot 2026-11-17.