Updated
GPT-6.1 Sol vs GPT-6 Luna
GPT-6 Luna had 54% fewer counted bugs per line than GPT-6.1 Sol (0.45 vs 0.98).
| GPT-6.1 Sol | GPT-6 Luna | |
|---|---|---|
| Bug rate | ||
| Relative bug rate | 0.98 | 0.45 |
| Rank | #2 of 7 | #1 of 7 |
| By coding agent | ||
| Codex | 0.98 | 0.44 |
| By language | ||
| TypeScript(statistically tied) | 1.06 | 0.73 |
| Details | ||
| Provider | OpenAI | OpenAI |
| Released | Sep 29, 2026 | Sep 22, 2026 |
| List price | $2 input / $10 output per 1M tokens | $0.10 input / $0.50 output per 1M tokens |
| Share of AI-written code, week of Oct 12 | 9.5% | 1.4% |
1.00 = average · lower is better · = statistically tied
More comparisons
Questions and answers
- Which has fewer bugs, GPT-6.1 Sol or GPT-6 Luna?
- GPT-6 Luna had 54% fewer counted bugs per line than GPT-6.1 Sol (0.45 vs 0.98). GPT-6 Luna ranks #1 of 7 and GPT-6.1 Sol #2.
- Which is cheaper, GPT-6.1 Sol or GPT-6 Luna?
- GPT-6.1 Sol lists at $2 input / $10 output per 1M tokens; GPT-6 Luna lists at $0.10 input / $0.50 output per 1M tokens. GPT-6 Luna has the lower list price.
- Does it depend on the programming language?
- In TypeScript, they were statistically tied (1.06 and 0.73).
- Which is used more, GPT-6.1 Sol or GPT-6 Luna?
- GPT-6.1 Sol, with 9.5% of the AI-written code reviewed by cubic in the week of Oct 12, 2026, against 1.4% for GPT-6 Luna.