claude-opus-5
claude-opus-5 has 3 tested configurations. Its highest published overall score is 81.70 at max. Inspect dimension scores, evaluation time, and reference cost below.
Overall score81.70
claude-opus-5 · max
- Backend engineering
- 70
- Frontend interaction
- 87
- Knowledge & Reasoning
- 95
- Visual aesthetics
- 73
- Maintainability
- 61
- Evaluation time
- 92m 12s
- Reference cost
- $7.99
Complete evaluation · API reference cost
Results by reasoning effort
Swipe to see all results →
| Model / effort | Overall | Backend engineering | Frontend interaction | Knowledge & Reasoning | Visual aesthetics | Maintainability | Total eval. time | Total ref. cost | Compare |
|---|---|---|---|---|---|---|---|---|---|
| 76.95 | 68 | 85 | 90 | 61 | 57 | 66m 37s | $4.06 | ||
| 77.75 | 74 | 87 | 85 | 66 | 59 | 80m 26s | $5.68 | ||
| 81.70 | 70 | 87 | 95 | 73 | 61 | 92m 12s | $7.99 |
Score breakdown
- Overall score
- 81.70
- Evaluation time
- 92m 12s
- Reference cost
- $7.99
Service logic, error handling, and test verification.
Contracts and boundaries11 / 20
API contracts, input validation, and boundary behavior.
Retries and failures15 / 20
Error recovery, retry conditions, and failure handling.
CI and adversarial review14 / 20
Verification plans, risk detection, and audit evidence.
Transactions and consistency15 / 20
State transitions, concurrency control, and data consistency.
Caching and regression15 / 20
Cache 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
- +4.0 pts 77.75 → 81.70
- Reference cost
- +$2.32 $5.68 → $7.99
- Evaluation time
- +14.6% 80m 26s → 92m 12s
Data snapshot published · 10/27/2026Scoring & cost notes