←Story detail

Trending story

Arena.ai Publishes Per-Task Cost Comparison of Models on Agent Arena

1 reports1 story updatesUpdated Oct 30 00:38

Understand this story

AI overview

Arena.ai published a per-task cost comparison of models on Agent Arena on October 30, 2026. Statistics show that OpenAI's GPT-6.1 Sol (Max) costs $1.91 per task, 85% lower than Claude Opus 5.5 (Max) at $12.51 and 87% lower than GPT-6 Astra (Max) at $14.93. Arena.ai noted that these two cost advantages come from different sources: relative to Astra, Sol's advantage mainly comes from a lower per-token price; relative to Opus, it mainly comes from consuming fewer tokens per task. Per-task cost is calculated by multiplying the number of input, output, and cache-read tokens by their respective unit prices, and Arena.ai identifies the reasons for the cost reduction by comparing prices and token usage.

AI-generated from public reports

Latest development · Report

Arena Analysis: Agent Arena Cost per Task: GPT-6.1 Sol at $1.91

Developments

1 confirmed developments

  1. Arena.ai publishes per-task cost comparison of models on Agent Arena

    Source:Arena

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Oct 30

  1. Arena

    Arena Analysis: Agent Arena Cost per Task: GPT-6.1 Sol at $1.91

    Arena's statistics on Agent Arena show that OpenAI's GPT-6.1 Sol (Max) costs $1.91 per task, 85% less than Claude Opus 5.5 (Max) at $12.51 and 87% less than GPT-6 Astra (Max) at $14.93. Arena notes that the sources of these two cost advantages differ: relative to Astra, Sol's advantage comes mainly from a lower token unit price; relative to Opus, it comes mainly from consuming fewer tokens per task. Cost per task is calculated by multiplying the number of input, output, and cache-read tokens by their respective unit prices, and Arena pinpoints the causes of cost reductions by comparing prices and token usage.

Related stories

  1. Related storiesArtificial Analysis showcases comparison of two models' performance on the same robotic task
  2. Related storiesArena.ai compares coding agent user criticism across 20,869 traces
  3. Related storiesCognition Launches Coding Benchmark FrontierCode 2.0
  4. Related storiesKimi official account releases Kimi K3.1 teaser video