--- title: EsoLang-Bench: Evaluating LLMs via Esoteric Programming... description: EsoLang-Bench is a new benchmark of 80 programming problems across five esoteric languages (Brainfuck, Befunge-98, Whitespace, Unlambda, and Shakespeare)... canonical: https://daily.dev/posts/esolang-bench-evaluating-llms-via-esoteric-programming-languages-5ruzdvsxd twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: EsoLang-Bench: Evaluating LLMs via Esoteric Programming Languages | daily.dev og:description: EsoLang-Bench is a new benchmark of 80 programming problems across five esoteric languages (Brainfuck, Befunge-98, Whitespace, Unlambda, and Shakespeare)... og:url: https://daily.dev/posts/esolang-bench-evaluating-llms-via-esoteric-programming-languages-5ruzdvsxd og:image: https://api.daily.dev/og/posts/5rUZDVSxD.png og:image:alt: EsoLang-Bench: Evaluating LLMs via Esoteric Programming Languages og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # EsoLang-Bench: Evaluating LLMs via Esoteric Programming Languages **[Hacker News](https://daily.dev/sources/hn)** · 5 min read · 1 upvotes · 0 comments ## Summary EsoLang-Bench is a new benchmark of 80 programming problems across five esoteric languages (Brainfuck, Befunge-98, Whitespace, Unlambda, and Shakespeare) designed to test genuine reasoning in LLMs rather than memorization. Training data for these languages is 5,000–100,000x scarcer than Python. Frontier models that score ~90% on standard Python benchmarks collapse to single-digit accuracy here, with the best model achieving only 3.8% overall. All models score 0% on Medium difficulty and above, and Whitespace remains completely unsolved. Few-shot prompting offers no improvement over zero-shot, suggesting standard benchmark success reflects training data memorization. Tool-augmented agentic systems (Codex, Claude Code) achieve roughly 2× the accuracy of prompting-only approaches via execution feedback loops, but still fall far short of mainstream language performance. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [\[2605.03546\] ProgramBench: Can Language Models Rebuild Programs From Scratch?](https://daily.dev/posts/2605-03546-programbench-can-language-models-rebuild-programs-from-scratch--pnyvfwifh) · Hacker News · 0 upvotes · 0 comments - [CodeClash Benchmarks LLMs through Multi-Round Coding Competitions](https://daily.dev/posts/codeclash-benchmarks-llms-through-multi-round-coding-competitions-e95odpbm0) · InfoQ · 2 upvotes · 0 comments - [Most coding agent benchmarks skip large-scale refactoring. Not this one.](https://daily.dev/posts/most-coding-agent-benchmarks-skip-large-scale-refactoring-not-this-one--p55v6sihn) · The New Stack · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm) [View this post on daily.dev](https://daily.dev/posts/esolang-bench-evaluating-llms-via-esoteric-programming-languages-5ruzdvsxd) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"EsoLang-Bench: Evaluating LLMs via Esoteric Programming Languages","url":"https://daily.dev/posts/esolang-bench-evaluating-llms-via-esoteric-programming-languages-5ruzdvsxd","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/esolang-bench-evaluating-llms-via-esoteric-programming-languages-5ruzdvsxd"},"datePublished":"2026-03-20T05:21:03.055Z","dateModified":"2026-03-20T05:21:28.691Z","description":"EsoLang-Bench is a new benchmark of 80 programming problems across five esoteric languages (Brainfuck, Befunge-98, Whitespace, Unlambda, and Shakespeare)...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/531821d8e0f48463460a80dea505f0c6?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/531821d8e0f48463460a80dea505f0c6?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/esolang-bench-evaluating-llms-via-esoteric-programming-languages-5ruzdvsxd","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"EsoLang-Bench: Evaluating LLMs via Esoteric Programming Languages"}]} ```