Kaggle MultiLoKo - Traditional Mandarin: leaderboard
Metric: Exact Match (%). Source: www.kaggle.com. 48 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 75.4 |
| 2 | Gemini 3.5 Flash | 66.8 |
| 3 | Gemini 3 Flash (Preview) | 66.8 |
| 4 | Gemini 2.5 Pro (Preview 06-05) | 57.6 |
| 5 | Gemini 3.1 Flash Lite (Preview) | 56.8 |
| 6 | DeepSeek V3 | 47.2 |
| 7 | DeepSeek R1 0528 | 47.2 |
| 8 | Gemini 2.0 Flash | 46.8 |
| 9 | Gemini 2.5 Flash (Preview 05-20) | 46.4 |
| 10 | GPT-5.4 | 45.2 |
| 11 | O1 | 43.6 |
| 12 | GPT-5 | 43.2 |
| 13 | Claude Opus 4 | 42.8 |
| 14 | Claude Opus 4.1 | 41.6 |
| 15 | Gemini 1.5 Pro (002) | 40.8 |
Interactive version: theaggregate.ai/benchmark?slug=kaggle-multiloko-traditional-mandarin · How It Works · Data refreshed daily, snapshot 2026-09-19.