OpenAI released GPT-6 Sol and GPT-6 Luna on September 22, both at half the API price or less of the GPT-5.6 models they replace: $2 and $10 per million input and output tokens for Sol, $0.10 and $0.50 for Luna. OpenAI says Sol at max effort nearly matches Claude Fable 5 on its software engineering benchmark at a fifth of the cost, and that Luna at max effort lands near Claude Opus 5. We graded both as the successors to GPT-5.6 Sol and GPT-5.6 Luna.
What the results show
- GPT-6 Sol is a step back. GPT-6 Sol fixes fewer real issues than GPT-5.6 Sol and falls from fourth place to seventh. It fails one of the easiest real issues on the bench, one that Claude Haiku 4.5 and Composer 2.5 solve. We reran that task twice to rule out a fluke and read the logs, and it simply does not manage it.
- It is light on the plan. On the $20 ChatGPT Plus plan a run of our suites takes well under half the weekly usage of GPT-5.6 Sol, and it answers faster too. At the same monthly price it goes further per session than Claude Opus 5.5: a run fits in about half of a five-hour window, where Opus 5.5 would need slightly more than a whole one. Over the week the two come out about even, at around 5% of the limit.
- GPT-6 Luna is faster, but not better. GPT-6 Luna lands on the same low grade as GPT-5.6 Luna and still struggles with one-line bug reports. It answers about three times as fast and barely touches the plan.
Our take: neither model is worth switching to for coding, and that matches our own use. GPT-5.6 Sol is still in Codex and stays the better OpenAI pick. With this release a Claude subscription becomes the clear choice even at $20, without needing Fable, because Opus 5.5 fixes far more for about the same weekly usage. GPT-6 works differently from the GPT-5.6 models under the hood and Codex takes time to adjust to a new model line, so we expect both to improve over the coming weeks. We are still waiting on results for Grok 4.7, but from the chatter online it does not seem to perform that well.
Grades are comparable within the same suite version. See the full GPT-6 Sol and GPT-6 Luna scorecards or follow the field over time on Trends.