Claude Fable 5.1
Claude Fable 5.1 has 3 tested configurations. Its highest published overall score is 89.0 at max. Inspect dimension scores, evaluation time, and cost below.
Overall score89.0
Claude Fable 5.1 · max
- Backend engineering
- 83
- Frontend interaction
- 91
- Knowledge & reasoning
- 95
- Evaluation time
- 79m 7s
- Cost
- $26.15
Complete evaluation · API cost
Results by reasoning effort
Swipe to see all results →
| Model / effort | Overall | Backend engineering | Frontend interaction | Knowledge & reasoning | Total eval. time | Total ref. cost | Compare |
|---|---|---|---|---|---|---|---|
| 79.3 | 70 | 81 | 90 | 66m 53s | $8.28 | ||
| 87.9 | 81 | 90 | 95 | 55m 35s | $15.94 | ||
| 89.0 | 83 | 91 | 95 | 79m 7s | $26.15 |
Score breakdown
- Overall score
- 89.0
- Evaluation time
- 79m 7s
- Cost
- $26.15
Service logic, error handling and verification.
Contracts and boundaries13 / 20
API contracts, input validation and boundary behavior.
Retries and failures20 / 20
Recovery, retry conditions and failure handling.
CI and adversarial review14 / 20
Verification plans, risk detection and audit evidence.
Transactions and consistency19 / 20
State transitions, concurrency and consistency.
Caching and regression17 / 20
Invalidation, data updates and regression coverage.
What changes with higher reasoning effort
Compare overall scores, cost, and time across neighboring tested efforts.
xhigh max
- Overall
- +1.1 pts 87.9 → 89.0
- Cost
- +$10.21 $15.94 → $26.15
- Evaluation time
- +42.3% 55m 35s → 79m 7s
Data snapshot published · 11/13/2026Scoring & cost notes