DeepSeek V4 Pro
DeepSeek V4 Pro has 2 tested configurations. Its highest published overall score is 63.1 at max. Inspect dimension scores, evaluation time, and cost below.
Overall score63.1
DeepSeek V4 Pro · max
- Backend engineering
- 64
- Frontend interaction
- 60
- Knowledge & reasoning
- 65
- Evaluation time
- 93m 15s
- Cost
- $1.15
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 |
|---|---|---|---|---|---|---|---|
| 59.9 | 56 | 50 | 75 | 61m 4s | $0.98Partial cost | ||
| 63.1 | 64 | 60 | 65 | 93m 15s | $1.15 |
Score breakdown
- Overall score
- 63.1
- Evaluation time
- 93m 15s
- 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 regression13 / 20
Invalidation, data updates and regression coverage.
What changes with higher reasoning effort
Compare overall scores, cost, and time across neighboring tested efforts.
high max
- Overall
- +3.2 pts 59.9 → 63.1
- Cost
- — — → $1.15
- Evaluation time
- +52.7% 61m 4s → 93m 15s
Data snapshot published · 11/13/2026Scoring & cost notes