Model comparison
Selected 2 / 5See the differences. Choose what matters to you.
Available modelsSelected 2 / 5
Differences vs. k3.1-pro · high
Score, cost & time differences
Current baseline · k3.1-pro · high
80Knowledge & Reasoning
Compared with k3.1-pro · high
- k3.1-pro · max
Knowledge & Reasoning: tiedReference cost $2.38 ($1.97 more)Evaluation time 45m 47s (35m 48s more)
Differences reflect these evaluation tasks. Cost and time cover the same dimension, not a typical conversation. Scoring & cost notes
| Metric | k3.1-pro · high | k3.1-pro · max |
|---|---|---|
| Knowledge & Reasoning | k3.1-prohigh 80 | k3.1-promax 80Tied |
| Overall | k3.1-prohigh 76.10 | k3.1-promax 79.60+3.5 pts |
| Backend engineering | k3.1-prohigh 72 | k3.1-promax 84+12 pts |
| Frontend interaction | k3.1-prohigh 87 | k3.1-promax 91+4 pts |
| Visual aesthetics | k3.1-prohigh 68 | k3.1-promax 68Tied |
| Maintainability | k3.1-prohigh 61 | k3.1-promax 64+3 pts |
Knowledge & Reasoning evaluation · Evaluation consumption, not a monthly subscription fee
Cost & time
Knowledge & Reasoning evaluation| Metric | k3.1-pro · high | k3.1-pro · max |
|---|---|---|
| Reference cost | k3.1-prohigh $0.41 | k3.1-promax $2.38+$1.97 |
| Evaluation time | k3.1-prohigh 9m 59s | k3.1-promax 45m 47s+358.5% |
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 | k3.1-prohigh | k3.1-promax |
|---|---|---|
| Contracts and boundaries | 14 / 20 | 16 / 20 |
| Retries and failures | 16 / 20 | 18 / 20 |
| CI and adversarial review | 11 / 20 | 13 / 20 |
| Transactions and consistency | 14 / 20 | 19 / 20 |
| Caching and regression | 17 / 20 | 18 / 20 |
Frontend interactionSubscores
| Scoring dimension | k3.1-prohigh | k3.1-promax |
|---|---|---|
| Layout and adaptation | 18 / 20 | 20 / 20 |
| Interaction behavior | 20 / 20 | 20 / 20 |
| State continuity | 15 / 20 | 15 / 20 |
| Accessibility and feedback | 13 / 15 | 15 / 15 |
| State validation and regression | 21 / 25 | 21 / 25 |
Knowledge & ReasoningSubscores
| Scoring dimension | k3.1-prohigh | k3.1-promax |
|---|---|---|
| Mathematical reasoning | 10 / 15 | 15 / 15 |
| Computer science & AI | 5 / 15 | 5 / 15 |
| Science and engineering | 10 / 10 | 10 / 10 |
| Life sciences and medicine | 15 / 20 | 15 / 20 |
| Humanities and general knowledge | 40 / 40 | 35 / 40 |
Visual aestheticsSubscores
| Scoring dimension | k3.1-prohigh | k3.1-promax |
|---|---|---|
| Composition | 19 / 20 | 20 / 20 |
| Spacing and alignment | 17 / 20 | 15 / 20 |
| Typography and expression | 17 / 20 | 16 / 20 |
| Color and surfaces | 19 / 20 | 20 / 20 |
| Control styling | 16 / 20 | 17 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.
MaintainabilitySubscores
| Scoring dimension | k3.1-prohigh | k3.1-promax |
|---|---|---|
| Semantic clarity | 15 / 20 | 16 / 20 |
| Control-flow organization | 20 / 20 | 20 / 20 |
| Locality of changes | 15 / 20 | 15 / 20 |
| State and lifecycle | 18 / 20 | 18 / 20 |
| Implementation economy | 17 / 20 | 17 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.