Model comparison
Selected 2 / 5See the differences. Choose what matters to you.
Differences vs. deepseek-v4-pro · high
Score, cost & time differences
Current baseline · deepseek-v4-pro · high
75Knowledge & Reasoning
Compared with deepseek-v4-pro · high
- deepseek-v4.1-flash-1017 · max
Knowledge & Reasoning: tiedComparable cost unavailableEvaluation time 28m 33s (6m 44s more)
Differences reflect these evaluation tasks. Cost and time cover the same dimension, not a typical conversation. Scoring & cost notes
| Metric | deepseek-v4-pro · high | deepseek-v4.1-flash-1017 · max |
|---|---|---|
| Knowledge & Reasoning | deepseek-v4-prohigh 75 | deepseek-v4.1-flash-1017max 75Tied |
| Overall | deepseek-v4-prohigh 63.60 | deepseek-v4.1-flash-1017max 74.30+10.7 pts |
| Backend engineering | deepseek-v4-prohigh 61 | deepseek-v4.1-flash-1017max 72+11 pts |
| Frontend interaction | deepseek-v4-prohigh 54 | deepseek-v4.1-flash-1017max 96+42 pts |
| Visual aesthetics | deepseek-v4-prohigh 59 | deepseek-v4.1-flash-1017max 61+2 pts |
| Maintainability | deepseek-v4-prohigh 55 | deepseek-v4.1-flash-1017max 53−2 pts |
Knowledge & Reasoning evaluation · Evaluation consumption, not a monthly subscription fee
Cost & time
Knowledge & Reasoning evaluation| Metric | deepseek-v4-pro · high | deepseek-v4.1-flash-1017 · max |
|---|---|---|
| Reference cost | deepseek-v4-prohigh N/A | deepseek-v4.1-flash-1017max $0.27 |
| Evaluation time | deepseek-v4-prohigh 21m 50s | deepseek-v4.1-flash-1017max 28m 33s+30.8% |
Capability profiles
Show up to five models. Select names to focus the chart.
Behind each score
Expand to inspect each subaxis.
Backend engineeringSubscores
| Scoring dimension | deepseek-v4-prohigh | deepseek-v4.1-flash-1017max |
|---|---|---|
| Contracts and boundaries | 10 / 20 | 17 / 20 |
| Retries and failures | 16 / 20 | 15 / 20 |
| CI and adversarial review | 8 / 20 | 11 / 20 |
| Transactions and consistency | 13 / 20 | 14 / 20 |
| Caching and regression | 14 / 20 | 15 / 20 |
Frontend interactionSubscores
| Scoring dimension | deepseek-v4-prohigh | deepseek-v4.1-flash-1017max |
|---|---|---|
| Layout and adaptation | 15 / 20 | 20 / 20 |
| Interaction behavior | 12 / 20 | 20 / 20 |
| State continuity | 5 / 20 | 20 / 20 |
| Accessibility and feedback | 7 / 15 | 11 / 15 |
| State validation and regression | 15 / 25 | 25 / 25 |
Knowledge & ReasoningSubscores
| Scoring dimension | deepseek-v4-prohigh | deepseek-v4.1-flash-1017max |
|---|---|---|
| Mathematical reasoning | 10 / 15 | 15 / 15 |
| Computer science & AI | 10 / 15 | 15 / 15 |
| Science and engineering | 5 / 10 | 5 / 10 |
| Life sciences and medicine | 20 / 20 | 15 / 20 |
| Humanities and general knowledge | 30 / 40 | 25 / 40 |
Visual aestheticsSubscores
| Scoring dimension | deepseek-v4-prohigh | deepseek-v4.1-flash-1017max |
|---|---|---|
| Composition | 19 / 20 | 19 / 20 |
| Spacing and alignment | 13 / 20 | 15 / 20 |
| Typography and expression | 16 / 20 | 16 / 20 |
| Color and surfaces | 20 / 20 | 19 / 20 |
| Control styling | 16 / 20 | 16 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.
MaintainabilitySubscores
| Scoring dimension | deepseek-v4-prohigh | deepseek-v4.1-flash-1017max |
|---|---|---|
| Semantic clarity | 15 / 20 | 15 / 20 |
| Control-flow organization | 19 / 20 | 19 / 20 |
| Locality of changes | 14 / 20 | 14 / 20 |
| State and lifecycle | 17 / 20 | 17 / 20 |
| Implementation economy | 17 / 20 | 16 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.