Research

Arena Team

Published on 4 Dec 2025
Last updated on 4 Dec 2025
Reading Time: 1 minute

Studying the Frontier: Arena Expert

Arena Expert is a great way to differentiate between frontier models. In this analysis, we compare how models perform on 'general' vs 'expert' prompts, focusing on 'thinking' vs 'non-thinking' models.

Share this Article

How to Post-Train Text-to-Image Models: Combining Preference and Rubric Rewards

We introduce a post-training approach that combines human preference signals with explicit rubric-based rewards. Trained on 5M Arena pairwise preference votes, it pushes FLUX.2-dev to #2 on the live T2I leaderboard and Ideogram 4 past every publicly listed open-source model.

Research

Arena Team—2 Oct 2026

HarnessTax: How Much Does the Harness Matter for Coding Agents?

We tested 21 coding agent model–harness combinations across Claude Code, Codex CLI, and Pi to understand how harness choice affects performance and cost. The results show that harness choice can significantly impact cost, even when task success rates are similar.

Research

Arena Team—16 Sept 2026

Call for Proposals: Arena's Academic Partnerships Program, Fall 2026

Arena's Academic Partnerships Program opens a call for research proposals twice a year, every Spring and Fall. We're excited to open the Fall 2026 cycle today, with submissions due October 30, 2026.

Arena Team—1 Sept 2026

Announcing the First Cohort of Arena's Academic Partnerships Program

We're glad to introduce the first cohort of researchers supported through the Arena Academic Partnerships program.

Arena Team—1 Sept 2026

Coding in Agent Mode: From Idea to Shipping with GitHub

AI coding assistants have fundamentally changed how code is created. But for most developers, a chat interface has been a "read-only" or "copy-paste" coding experience — until now.

Product

Arena Team—24 Aug 2026

Agent Leaderboard Improvements: Categories & Task Cost

Agents are being asked to do a wide variety of work. This means a single, performance-only agentic leaderboard is no longer sufficient. Two questions decide which model to use: what’s best for my specific kind of task, and what will it cost to get that task done? We aim to help answer these questions with our latest update to Agent Arena.

Product

Arena Team—14 Aug 2026

Introducing AutoEval to the Arena leaderboards

At Arena, our evaluations are dynamic and grounded in real-world use. But real-world signals take time to collect. Today, we’re introducing AutoEval scores to provide immediate, calibrated model ratings on real tasks when waiting for human votes to accumulate.

Product

Arena Team—30 Jul 2026

Text Arena and Search Arena scores with the factuality adjustment on

Factuality in the Arena

Factuality remains one of the most persistent questions users face when using AI models. Today, we are launching a leaderboard that ranks models not only by human preference, but also by the factual accuracy of their responses.

Research

Product

Arena Team—14 Jul 2026

Build, Deploy, and Evaluate with Fullstack Code Arena

Code Arena has evolved beyond frontend prototyping into a complete fullstack AI development platform. Explore capabilities like databases, authentication, third-party integrations, and deployments, and see how Fullstack Code Arena helps developers, entrepreneurs, and AI labs build, deploy, and evaluate production-ready applications.

Product

Arena Team—2 Jul 2026

See All Articles

Studying the Frontier: Arena Expert

Share this Article

Related Articles

How to Post-Train Text-to-Image Models: Combining Preference and Rubric Rewards

HarnessTax: How Much Does the Harness Matter for Coding Agents?

Call for Proposals: Arena's Academic Partnerships Program, Fall 2026

Announcing the First Cohort of Arena's Academic Partnerships Program

Coding in Agent Mode: From Idea to Shipping with GitHub

Agent Leaderboard Improvements: Categories & Task Cost

Introducing AutoEval to the Arena leaderboards

Factuality in the Arena

Build, Deploy, and Evaluate with Fullstack Code Arena

Subscribe
to Arena news and research

Studying the Frontier: Arena Expert

Share this Article

Related Articles

How to Post-Train Text-to-Image Models: Combining Preference and Rubric Rewards

HarnessTax: How Much Does the Harness Matter for Coding Agents?

Call for Proposals: Arena's Academic Partnerships Program, Fall 2026

Announcing the First Cohort of Arena's Academic Partnerships Program

Coding in Agent Mode: From Idea to Shipping with GitHub

Agent Leaderboard Improvements: Categories & Task Cost

Introducing AutoEval to the Arena leaderboards

Factuality in the Arena

Build, Deploy, and Evaluate with Fullstack Code Arena

Subscribe
to Arena news and research

Studying the Frontier: Arena Expert

Share this Article

Related Articles

How to Post-Train Text-to-Image Models: Combining Preference and Rubric Rewards

HarnessTax: How Much Does the Harness Matter for Coding Agents?

Call for Proposals: Arena's Academic Partnerships Program, Fall 2026

Announcing the First Cohort of Arena's Academic Partnerships Program

Coding in Agent Mode: From Idea to Shipping with GitHub

Agent Leaderboard Improvements: Categories & Task Cost

Introducing AutoEval to the Arena leaderboards

Factuality in the Arena

Build, Deploy, and Evaluate with Fullstack Code Arena

Subscribeto Arena news and research

Studying the Frontier: Arena Expert

Share this Article

Related Articles

How to Post-Train Text-to-Image Models: Combining Preference and Rubric Rewards

HarnessTax: How Much Does the Harness Matter for Coding Agents?

Call for Proposals: Arena's Academic Partnerships Program, Fall 2026

Announcing the First Cohort of Arena's Academic Partnerships Program

Coding in Agent Mode: From Idea to Shipping with GitHub

Agent Leaderboard Improvements: Categories & Task Cost

Introducing AutoEval to the Arena leaderboards

Factuality in the Arena

Build, Deploy, and Evaluate with Fullstack Code Arena

Subscribeto Arena news and research

Subscribe
to Arena news and research

Subscribe
to Arena news and research