TurkBench - Turkish General Knowledge: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 38 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5 FP8 | 85.94 |
| 2 | Qwen 3.5 397B A17B | 84.9 |
| 3 | GLM-4.6 | 83.85 |
| 4 | Qwen 3.5 122B A10B | 81.25 |
| 5 | MiniMax-M2 | 80.21 |
| 6 | GPT-OSS-120B | 77.6 |
| 7 | DeepSeek V3.1 | 77.6 |
| 8 | DeepSeek V3.2 Exp | 77.6 |
| 9 | MiniMax-M2.5 | 77.6 |
| 10 | Qwen 3.5 27B | 75.52 |
| 11 | Qwen 3.5 35B A3B | 75.52 |
| 12 | Step 3.5 Flash | 75.52 |
| 13 | MiMo-V2-Flash | 75 |
| 14 | Gemma 3 27B (IT) | 74.65 |
| 15 | Gemma 3 12B (IT) | 71.35 |
Interactive version: theaggregate.ai/benchmark?slug=turkbench-turkish-general-knowledge · How It Works · Data refreshed daily, snapshot 2026-09-19.