Kaggle MultiLoKo - Turkish 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 February 2028. 16 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)68.4#99
2Gemini 3.8 Flash64.4#39
3GPT-6.1 Sol58.8#12
4GPT-6 Astra58.4#8
5Gemini 4 Argon54#14
6GPT-6 Luna44#105
7Qwen 3.8 Max43.2#64
8Grok 4.740.8#48
9GLM-534#267
10Claude Opus 5.527.2#7
11Kimi K326.8#59
12Claude Opus 4.824#62
13Claude Sonnet 5.523.2#21
14Gemma 4 31B22.4#385
15Claude Sonnet 519.6#118

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-turkish-task-v7 · How It Works · Data refreshed daily, snapshot 2026-11-17.