Updated
Best AI coding models, November 2026 edition
As of Nov 9, 2026, GPT-6 Luna had the lowest relative bug rate on Bug Bench (0.31, 69% fewer counted bugs than average), among 7 ranked AI coding models. Updates daily until Nov 30.
| Rank | Model | Rate |
|---|---|---|
| 1 | GPT-6 Luna | 0.31 |
| 2 | GPT-6.1 Sol | 0.74 |
| 3= (statistically tied) | Claude Fable 5.1 | 0.88 |
| 4= (statistically tied) | GPT-6 Astra | 0.95 |
| 5= (statistically tied) | Claude Sonnet 5.5 | 1.04 |
| 6= (statistically tied) | Claude Opus 5.5 | 1.11 |
| 7 | Grok 4.7 | 1.61 |
1.00 = average · lower is better · = statistically tied
Most-used models and coding agents
Share of AI-written code, week of Nov 2
Models
- Claude Opus 5.5
- 66.2%
- GPT-6.1 Sol
- 9.9%
- GPT-6 Astra
- 4.5%
- Claude Sonnet 5.5
- 3.7%
- Claude Fable 5.1
- 2.8%
Coding agents
- Claude Code
- 79.4%
- Codex
- 16.1%
- Cursor
- 1.9%