Kaggle MultiLoKo - Average v2 (Tasks v6, German v3, Korean and Turkish 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 June 2028. 16 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 57.03 | #99 |
| 2 | Gemini 3.8 Flash | 53.23 | #39 |
| 3 | GPT-6.1 Sol | 52.85 | #12 |
| 4 | GPT-6 Astra | 52.81 | #8 |
| 5 | Gemini 4 Argon | 47.57 | #14 |
| 6 | GPT-6 Luna | 40.65 | #105 |
| 7 | Grok 4.7 | 36.76 | #48 |
| 8 | Qwen 3.8 Max | 35.95 | #64 |
| 9 | Claude Opus 5.5 | 32.93 | #7 |
| 10 | GLM-5 | 31.3 | #267 |
| 11 | Kimi K3 | 28 | #59 |
| 12 | Claude Sonnet 5.5 | 26.67 | #21 |
| 13 | Claude Opus 4.8 | 22.44 | #62 |
| 14 | GLM-5.3 Flash | 22.27 | #136 |
| 15 | Claude Sonnet 5 | 22.01 | #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-average-v2-tasks-v6-german-v3-korean-and-turkish-v7 · How It Works · Data refreshed daily, snapshot 2026-11-17.