GPT-6 Sol vs. Claude Opus 5.5: Is cheaper important when results aren’t consistent?
OpenAI launched GPT-6 Sol on September 22, claiming it scores higher than Claude Opus 5 on business workflow tasks at The post GPT-6 Sol vs. Claude Opus 5.5: Is cheaper important when results aren’t consistent? appeared first on The New Stack .
On September 22, OpenAI unveiled GPT-6 Sol, touting that it outperforms Claude Opus 5 on business workflow tasks at a fraction of the cost per task. Anthropic released Opus 5.5 on the same day, so a test was conducted against the newer model. Pricing-wise, GPT-6 Sol costs $2 per million input tokens and $10 per million output tokens, which is half the price of GPT-5.6 Sol. Opus 5.5 costs $4 and $20.
To examine their performance, the author chose to test the models on consistency. Both models performed equally well on standard developer tasks, so the tests were rebuilt to measure consistency. Surprisingly, the models gave different results. While Sol was faster and cheaper, Opus 5.5 was more accurate across all tests. Overall, Sol cost about a sixth of what Opus 5.5 did, and was 8% cheaper on CI triage, the test closest to OpenAI's claim. Though Sol was faster and cheaper, Opus 5.5 was more accurate and consistent.
Written by urgent.news from The New Stack's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
