DeepSeek V4.1 Flash (1017)
DeepSeek V4.1 Flash (1017) has 3 tested configurations. Its highest published overall score is 77.4 at max. Inspect dimension scores, evaluation time, and cost below.
Overall score77.4
DeepSeek V4.1 Flash (1017) · max
- Backend engineering
- 69
- Frontend interaction
- 91
- Knowledge & reasoning
- 75
- Evaluation time
- 64m 50s
- Cost
- —
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 |
|---|---|---|---|---|---|---|---|
| 69.3 | 60 | 81 | 70 | 27m 47s | $0.30 | ||
| 70.6 | 58 | 83 | 75 | 37m 29s | $0.26 | ||
| 77.4 | 69 | 91 | 75 | 64m 50s | — |
Score breakdown
- Overall score
- 77.4
- Evaluation time
- 64m 50s
- Cost
- N/A
Service logic, error handling and verification.
Contracts and boundaries17 / 20
API contracts, input validation and boundary behavior.
Retries and failures15 / 20
Recovery, retry conditions and failure handling.
CI and adversarial review11 / 20
Verification plans, risk detection and audit evidence.
Transactions and consistency14 / 20
State transitions, concurrency and consistency.
Caching and regression12 / 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
- +6.8 pts 70.6 → 77.4
- Cost
- — $0.26 → —
- Evaluation time
- +72.9% 37m 29s → 64m 50s
Data snapshot published · 11/13/2026Scoring & cost notes