Past battle · 2026-01-30 UTC
Large Language Models (LLMs) Showdown — January 30, 2026
From the Large Language Models (LLMs) category. 20 marks placed across 5 fighters. Brian Knows took the crown.
Final standings
The line-up
The fighters
Profiles of every tool that competed in this battle, ranked by their final score.
Brian Knows
An AI agent enabling natural language interactions with Web3 to execute transactions and retrieve on-chain data.
Brian Knows is an AI agent that enables users to interact with Web3 using natural language. It allows users to execute transactions and retrieve on-chain data through simple text-based commands. This tool aims to make Web3 more accessible by providing an intuitive interface for users to manage their digital assets and interact with blockchain networks. Brian Knows can be particularly useful for individuals who are familiar with Web3 but struggle with the technical complexities of interacting with blockchain networks directly. By leveraging AI, Brian Knows simplifies the process of executing transactions and retrieving data, making it easier for users to navigate the Web3 ecosystem.
Criteria breakdown
- Natural language processing
- Transaction execution
- On-chain data retrieval
- Web3 interaction
- AI-driven interface
Sakura AI
An interactive platform to chat with and create customizable AI characters for immersive role-play.
Sakura AI is an interactive platform where users can chat with and create customizable AI characters for immersive role-play. The platform allows users to engage in various scenarios, from everyday conversations to fantastical and horror-themed interactions. The platform hosts a variety of pre-created characters and scenarios, such as a homeless elf and her two-year-old daughter, a user's sister discovering their chatbot messages, and a group of teenage girls who summon a powerful demon. Users can also create their own characters, like Aiden, a popular kid in school who likes to tease the student council president, or Eva, a tsundere stepsister with a complex personality. The AI characters on Sakura AI are designed to have unique personalities, traits, and appearances. For instance, the teenage girls in the 'Unholy Party' scenario have distinct characteristics: Jasmine is confident and brave, Beatrice is a bookworm with a dorky and anxious personality, Claire is a tomboy who enjoys sports and adventure, Madison is the alpha bitch of her friend group, and Ellie is autistic and eccentric. The platform's focus is on providing an immersive role-play experience, allowing users to engage with AI characters in a chat-based environment. The interactions between users and AI characters drive the story forward, with an emphasis on balancing moments of tension and humor. Sakura AI seems to cater to users interested in creative storytelling, role-playing, and interactive fiction. However, without more information on the platform's features, pricing, and target audience, it's difficult to provide a comprehensive overview of its capabilities and limitations.
Criteria breakdown
- Character creation with unique personalities and appearances
- Interactive role-playing scenarios
- Customizable conversations and storylines
- User-generated content and community sharing
Log10 is a platform built to help teams improve the accuracy and reliability of large language model applications. It combines automated error detection with workflows that scale human expert review, making it easier to identify hallucinations, regressions, and quality issues as they happen in production. The platform logs LLM calls, surfaces problematic outputs, and trains custom auto-evaluators that learn from expert feedback. This lets engineering and domain teams continuously monitor model behavior, refine prompts, and ship more trustworthy AI features without manually inspecting every response.
Criteria breakdown
- LLM call logging and tracing
- Automated error and hallucination detection
- Expert feedback collection workflows
- Custom AI-powered evaluators
- Prompt management and versioning
- Production analytics dashboards
OpenAI operator (o1)
OpenAI's autonomous agent that operates browsers and apps to complete real-world tasks.
OpenAI Operator is an AI agent designed to take actions on a user's behalf, navigating websites, filling out forms, and interacting with software interfaces much like a human would. Built on OpenAI's reasoning models, it can break down multi-step goals into a sequence of browser actions and adapt when pages or workflows change. Typical use cases include booking travel, ordering groceries, scheduling appointments, gathering research, and assisting with repetitive software workflows. Users describe a goal in natural language and Operator executes it inside a controlled browser environment, pausing for confirmation when sensitive steps like payments or logins are involved. Operator is positioned as an early step toward general-purpose computer-using agents and is intended for users who want to offload routine digital chores rather than craft prompts for every step.
Criteria breakdown
- Browser-based task automation
- Natural language goal input
- Human-in-the-loop confirmations
- Multi-step planning and reasoning
- Session takeover and pause controls
- Support for travel, shopping, and research tasks
Resume Burger
AI-powered resume builder that turns your experience into interview-ready applications fast.
Resume Burger is an AI tool designed to help job seekers create polished resumes and prepare for interviews without the usual back-and-forth. It streamlines the process of translating your work history into a tailored document that aligns with the roles you're targeting. Beyond formatting, the platform aims to bridge the gap between submitting an application and landing an interview by offering tools that sharpen how candidates present themselves. Users input their background and let the AI handle structuring, wording, and optimization for relevant positions. It's positioned for anyone who wants to shorten the time between updating a resume and getting interview callbacks, from early-career applicants to professionals making a switch.
Criteria breakdown
- AI-generated resume drafting
- Interview preparation support
- Role-targeted content suggestions
- Fast resume-to-application workflow
- Editable templates and formatting
- Guided input for work history and skills