Model comparison
Selected 2 / 5See the differences. Choose what matters to you.
Available modelsSelected 2 / 5
Differences vs. Step-5 Preview · default
Score, cost & time differences
Current baseline · Step-5 Preview · default
62.90Overall
Compared with Step-5 Preview · default
- Kimi K2.8 (Coding) · high
Overall: −0.15 ptsCost $0.66 ($0.58 less)Evaluation time 70m 58s (27m 25s less)
Differences reflect these evaluation tasks. Cost and time cover the same dimension, not a typical conversation. Scoring & cost notes
| Metric | Step-5 Preview · default | Kimi K2.8 (Coding) · high |
|---|---|---|
| Overall | Step-5 Previewdefault 62.90 | Kimi K2.8 (Coding)high 62.75−0.15 pts |
| Backend engineering | Step-5 Previewdefault 56 | Kimi K2.8 (Coding)high 55−1 pts |
| Frontend interaction | Step-5 Previewdefault 61 | Kimi K2.8 (Coding)high 65+4 pts |
| Knowledge & reasoning | Step-5 Previewdefault 75 | Kimi K2.8 (Coding)high 70−5 pts |
| Visual aesthetics | Step-5 Previewdefault 47 | Kimi K2.8 (Coding)high 57+10 pts |
| Maintainability | Step-5 Previewdefault 55 | Kimi K2.8 (Coding)high 53−2 pts |
Complete evaluation · Evaluation consumption, not a monthly subscription fee
Cost & time
Complete evaluation| Metric | Step-5 Preview · default | Kimi K2.8 (Coding) · high |
|---|---|---|
| Cost | Step-5 Previewdefault $1.24 | Kimi K2.8 (Coding)high $0.66−$0.58 |
| Evaluation time | Step-5 Previewdefault 98m 22s | Kimi K2.8 (Coding)high 70m 58s−27.9% |
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 | Step-5 Previewdefault | Kimi K2.8 (Coding)high |
|---|---|---|
| Contracts and boundaries | 9 / 20 | 9 / 20 |
| Retries and failures | 16 / 20 | 15 / 20 |
| CI and adversarial review | 8 / 20 | 14 / 20 |
| Transactions and consistency | 16 / 20 | 9 / 20 |
| Caching and regression | 7 / 20 | 8 / 20 |
Frontend interactionSubscores
| Scoring dimension | Step-5 Previewdefault | Kimi K2.8 (Coding)high |
|---|---|---|
| Layout and adaptation | 18 / 20 | 16 / 20 |
| Interaction behavior | 13 / 20 | 16 / 20 |
| State continuity | 9 / 20 | 10 / 20 |
| Accessibility and feedback | 8 / 15 | 10 / 15 |
| State validation and regression | 13 / 25 | 13 / 25 |
Knowledge & reasoningSubscores
| Scoring dimension | Step-5 Previewdefault | Kimi K2.8 (Coding)high |
|---|---|---|
| Mathematical reasoning | 10 / 15 | 5 / 15 |
| Computer science & AI | 10 / 15 | 5 / 15 |
| Science and engineering | 10 / 10 | 5 / 10 |
| Life sciences and medicine | 20 / 20 | 20 / 20 |
| Humanities and general knowledge | 25 / 40 | 35 / 40 |
Visual aestheticsSubscores
| Scoring dimension | Step-5 Previewdefault | Kimi K2.8 (Coding)high |
|---|---|---|
| Composition | 15 / 20 | 16 / 20 |
| Spacing and alignment | 14 / 20 | 17 / 20 |
| Typography and expression | 15 / 20 | 16 / 20 |
| Color and surfaces | 18 / 20 | 19 / 20 |
| Control styling | 16 / 20 | 15 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.
MaintainabilitySubscores
| Scoring dimension | Step-5 Previewdefault | Kimi K2.8 (Coding)high |
|---|---|---|
| Semantic clarity | 15 / 20 | 14 / 20 |
| Control-flow organization | 19 / 20 | 19 / 20 |
| Locality of changes | 15 / 20 | 15 / 20 |
| State and lifecycle | 16 / 20 | 17 / 20 |
| Implementation economy | 17 / 20 | 16 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.