GPT-6 Sol surpasses Claude Opus 5 on Agents’ Last Exam at 60% lower cost
Summary
GPT-6 Sol outperforms Claude Opus 5 on the Agents' Last Exam benchmark while offering 60% lower cost, indicating a major advancement in AI model efficiency.
Similar Articles
Claude vs. OpenAI's GPT 6.1 Sol
An analysis comparing Anthropic's Claude Opus 5.5 (high effort) with OpenAI's GPT-6.1 Sol (xhigh effort) using Artificial Analysis data, finding Sol offers far better cost-efficiency at slightly lower intelligence, while Opus wins on latency and raw quality.
GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligence
OpenAI's GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, scoring near GPT-6 Astra on the Intelligence Index while costing less than a quarter per task and pushing the cost-efficiency Pareto frontier.
@chooi_jeq: On robotics tasks, GPT-6 Sol scores 1.6x as high as GPT-5.6 Sol and is 47% cheaper, but sits below the Pareto frontier …
GPT-6 Sol achieves 1.6x higher scores and 47% lower cost than GPT-5.6 Sol in robotics tasks, yet remains below the Pareto frontier of Opus 5.5.
OpenAI launches GPT-6.1 Sol, says it nearly matches GPT-6 Astra and costs less
OpenAI launched GPT-6.1 Sol, an AI model that nearly matches GPT-6 Astra's performance in agentic coding and professional tasks at a lower cost, with enhanced accuracy and safety features.
GPT-6 Sol Confirmed Weaker Than 5.6 Sol on Complex Tasks, But Wins on Cost and Efficiency
GPT-6 Sol is confirmed to be weaker than GPT-5.6 Sol on complex tasks, but it offers advantages in cost and efficiency.