Greek NLU Benchmark - Machine Translation: leaderboard
Greek NLU Benchmark v1.0 by KIEFER TEK, machine translation track of 436 items, kept out of the NLU average: chrF of model translations against the reference translations, 0-100, higher is better; a small board of seven models.
Metric: chrF (0-100). Source: huggingface.co. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 397B A17B | 82.11 | #154 |
| 2 | GLM-5.2 FP8 | 80.06 | #199 |
| 3 | MiniMax-M3 | 80 | #151 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=greek-nlu-benchmark-machine-translation · How It Works · Data refreshed daily, snapshot 2026-11-05.