PersLitEval: leaderboard
Despite impressive multilingual capabilities, large language models (LLMs) remain poorly evaluated on literary knowledge in non-English languages. We introduce PersLitEval, a benchmark of 4,514 Persian literature multiple-choice questions across eight fine-grained categories spanning spelling, literary devices, grammar, vocabulary, word formation, and conceptual understanding, sourced from materia
Metric: Overall Accuracy (%) (self-reported). Source: benchmarklist.com. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 50 | #343 |
| 2 | GPT-4.1 Mini | 48 | #355 |
| 3 | Gemini 2.5 Flash | 45 | #245 |
| 4 | Grok 4 Fast | 43 | #254 |
| 5 | Qwen2.5 72B Instruct | 40 | |
| 6 | Llama 3.3 70B Instruct | 38 | #534 |
Interactive version: theaggregate.ai/benchmark?slug=persliteval · How It Works · Data refreshed daily, snapshot 2026-10-20.