Updated
Claude Fable 5
As of Sep 26, 2026, Claude Fable 5 ranks #2 of 9 on Bug Bench with a relative bug rate of 0.70 (30% fewer counted bugs than average), statistically tied with GPT-5.6 Sol.
- Relative bug rate
- 0.70
- Rank of 9
- #2
- Tied with
- GPT-5.6 Sol
1.00 = average · lower is better
- Provider
- Anthropic
- Released
- Jun 9, 2026
- Price per 1M tokens
- $10 in · $50 out
- First seen
- Week of Jun 8
Nearby in the ranking
| Rank | Model | Rate |
|---|---|---|
| 1 | GPT-5.5 | 0.47 |
| 2 | Claude Fable 5 | 0.70 |
| 3= (statistically tied) | GPT-5.6 Sol | 0.73 |
| 4 | Claude Opus 4.8 | 0.88 |
Is Claude Fable 5 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 |
|---|---|---|
| 1 | Cursor | 0.17 |
| 1 | Claude Code | 0.72 |
How widely Claude Fable 5 is used
Share of AI-written code reviewed by cubic
- Latest weekWeek of Sep 14
- 0.9%
- This week so farSince Sep 21
- 0.2%
- Peak weekWeek of Jul 6
- 28.8%
Compare Claude Fable 5
Questions and answers
- Is Claude Fable 5 good for coding?
- Claude Fable 5 ranks #2 of 9 on Bug Bench, with 30% fewer counted bugs than average (0.70) from Jun 1 to Sep 20, 2026.
- Is Claude Fable 5 getting worse?
- Not enough weekly data yet (0 of 6 weeks).
- Which coding agent has the lowest bug rate with Claude Fable 5?
- Cursor (0.17), ahead of Claude Code (0.72).
Embed Claude Fable 5's Bug Bench badge
Markdown
[](https://www.cubic.dev/bugbench/models/claude-fable-5)HTML
<a href="https://www.cubic.dev/bugbench/models/claude-fable-5"><img src="https://www.cubic.dev/bugbench/badge/claude-fable-5" alt="Claude Fable 5 on Bug Bench" /></a>