Evals for Every Language - Hungarian (hu): leaderboard
Average score across evaluation tasks in Hungarian (hu), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 68 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 79.24 | #37 |
| 2 | Gemini 3.1 Flash Lite | 79.18 | #191 |
| 3 | Gemini 3.1 Pro (Preview) | 79.08 | #58 |
| 4 | Claude Opus 4.7 | 78.5 | #49 |
| 5 | Qwen 3.6 Plus | 78 | #120 |
| 6 | Claude Sonnet 4.6 | 77.66 | #90 |
| 7 | DeepSeek V3.1 | 76.63 | #264 |
| 8 | Claude Sonnet 4.5 | 76.11 | #142 |
| 9 | GPT-5 | 75.72 | #98 |
| 10 | Grok 4.20 | 75.66 | #175 |
| 11 | Claude Haiku 4.5 | 74.64 | #280 |
| 12 | GPT-5.3 | 74.45 | #103 |
| 13 | GPT-5.4 | 74.02 | #79 |
| 14 | Ministral 3 14B | 73.95 | #650 |
| 15 | Qwen 3 30B A3B 2507 Instruct | 73.24 | #488 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-hu · How It Works · Data refreshed daily, snapshot 2026-10-20.