Updated
Grok 4.7
As of Nov 4, 2026, Grok 4.7 ranks #8 of 8 on Bug Bench with a relative bug rate of 1.79 (79% more counted bugs than average).
- Relative bug rate
- 1.79
- Rank of 8
- #8
1.00 = average · lower is better
- Provider
- xAI
- Released
- Sep 21, 2026
- Price per 1M tokens
- $2 in · $6 out
- First seen
- Week of Sep 21
Nearby in the ranking
| Rank | Model | Rate |
|---|---|---|
| 6 | Claude Opus 4.8 | 1.16 |
| 7 | Claude Opus 5 | 1.21 |
| 8 | Grok 4.7 | 1.79 |
Is Grok 4.7 getting worse?
Not enough weekly data yet (0 of 6 weeks).
Where it does better or worse
# = rank among models
By coding agent
| Rank | Agent | Rate |
|---|---|---|
| 2 | Cursor | 1.77 |
By language
| Rank | Language | Rate |
|---|---|---|
| 8 | TypeScript | 1.75 |
| 8 | Python | 1.54 |
How widely Grok 4.7 is used
Share of AI-written code reviewed by cubic
- Latest weekWeek of Oct 26
- 1.1%
- This week so farSince Nov 2
- 1.2%
- Peak weekWeek of Oct 26
- 1.1%
Compare Grok 4.7
Questions and answers
- Is Grok 4.7 good for coding?
- Grok 4.7 ranks #8 of 8 on Bug Bench, with 79% more counted bugs than average (1.79) from Jul 13 to Nov 1, 2026.
- Is Grok 4.7 getting worse?
- Not enough weekly data yet (0 of 6 weeks).
- Which coding agent has the lowest bug rate with Grok 4.7?
- Cursor, at 1.77.
Embed Grok 4.7's Bug Bench badge
Markdown
[](https://www.cubic.dev/bugbench/models/grok-4-7)HTML
<a href="https://www.cubic.dev/bugbench/models/grok-4-7"><img src="https://www.cubic.dev/bugbench/badge/grok-4-7" alt="Grok 4.7 on Bug Bench" /></a>