deepseek-v4-pro
deepseek-v4-pro has 2 tested configurations. Its highest published overall score is 65.15 at max. See the axis results, time and cost below.
Overall score65.15
deepseek-v4-pro · max
- Backend engineering
- 67
- Frontend interaction
- 63
- Knowledge & reasoning
- 65
- Visual aesthetics
- 70
- Maintainability
- 59
- Evaluation time
- 93m 15s
- Reference cost
- $1.15
Complete evaluation · API reference cost
Score breakdown
- Overall
- 65.15
- Evaluation time
- 93m 15s
- Reference cost
- $1.15
Service logic, error handling and verification.
Contracts and boundaries9 / 20
API contracts, input validation and boundary behavior.
Retries and failures17 / 20
Recovery, retry conditions and failure handling.
CI and adversarial review12 / 20
Verification plans, risk detection and audit evidence.
Transactions and consistency13 / 20
State transitions, concurrency and consistency.
Caching and regression16 / 20
Invalidation, data updates and regression coverage.
What changes with more effort
Compare scores, cost and time at neighboring tested efforts.
high max
- Overall score
- +1.6 pts 63.60 → 65.15
- Reference cost
- — — → $1.15
- Evaluation time
- +52.7% 61m 4s → 93m 15s
Results by reasoning effort
Swipe to see all results →
| Model / effort | Overall | Backend engineering | Frontend interaction | Knowledge & reasoning | Visual aesthetics | Maintainability | Evaluation time | Reference cost | Compare |
|---|---|---|---|---|---|---|---|---|---|
| high | 63.60 | 61 | 54 | 75 | 59 | 55 | 61m 4s | $0.98Partial cost | |
| max | 65.15 | 67 | 63 | 65 | 70 | 59 | 93m 15s | $1.15 |
Data snapshot published · 10/13/2026Scoring & cost notes