Model comparison
Selected 2 / 5See the differences. Choose what matters to you.
Available modelsSelected 2 / 5
Differences vs. k2.8 · high
Score, cost & time differences
Current baseline · k2.8 · high
72Frontend interaction
Compared with k2.8 · high
- Gemini 3.7 Flash High · default
Frontend interaction: −1 ptsReference cost $0.058 ($0.19 less)Evaluation time 4m 35s (19m 24s less)
Differences reflect these evaluation tasks. Cost and time cover the same dimension, not a typical conversation. Scoring & cost notes
| Metric | k2.8 · high | Gemini 3.7 Flash High · default |
|---|---|---|
| Frontend interaction | k2.8high 72 | Gemini 3.7 Flash Highdefault 71−1 pts |
| Overall | k2.8high 63.55 | Gemini 3.7 Flash Highdefault 51.95−11.6 pts |
| Backend engineering | k2.8high 54 | Gemini 3.7 Flash Highdefault 63+9 pts |
| Knowledge & Reasoning | k2.8high 70 | Gemini 3.7 Flash Highdefault 25−45 pts |
| Visual aesthetics | k2.8high 57 | Gemini 3.7 Flash Highdefault 70+13 pts |
| Maintainability | k2.8high 53 | Gemini 3.7 Flash Highdefault 59+6 pts |
Frontend interaction evaluation · Evaluation consumption, not a monthly subscription fee
Cost & time
Frontend interaction evaluation| Metric | k2.8 · high | Gemini 3.7 Flash High · default |
|---|---|---|
| Reference cost | k2.8high $0.25 | Gemini 3.7 Flash Highdefault $0.058−$0.19 |
| Evaluation time | k2.8high 23m 59s | Gemini 3.7 Flash Highdefault 4m 35s−80.9% |
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 | k2.8high | Gemini 3.7 Flash Highdefault |
|---|---|---|
| Contracts and boundaries | 9 / 20 | 12 / 20 |
| Retries and failures | 15 / 20 | 16 / 20 |
| CI and adversarial review | 14 / 20 | 9 / 20 |
| Transactions and consistency | 9 / 20 | 12 / 20 |
| Caching and regression | 7 / 20 | 14 / 20 |
Frontend interactionSubscores
| Scoring dimension | k2.8high | Gemini 3.7 Flash Highdefault |
|---|---|---|
| Layout and adaptation | 16 / 20 | 13 / 20 |
| Interaction behavior | 18 / 20 | 18 / 20 |
| State continuity | 15 / 20 | 15 / 20 |
| Accessibility and feedback | 10 / 15 | 10 / 15 |
| State validation and regression | 13 / 25 | 15 / 25 |
Knowledge & ReasoningSubscores
| Scoring dimension | k2.8high | Gemini 3.7 Flash Highdefault |
|---|---|---|
| Mathematical reasoning | 5 / 15 | 5 / 15 |
| Computer science & AI | 5 / 15 | 0 / 15 |
| Science and engineering | 5 / 10 | 10 / 10 |
| Life sciences and medicine | 20 / 20 | 0 / 20 |
| Humanities and general knowledge | 35 / 40 | 10 / 40 |
Visual aestheticsSubscores
| Scoring dimension | k2.8high | Gemini 3.7 Flash Highdefault |
|---|---|---|
| Composition | 16 / 20 | 19 / 20 |
| Spacing and alignment | 17 / 20 | 17 / 20 |
| Typography and expression | 16 / 20 | 16 / 20 |
| Color and surfaces | 19 / 20 | 20 / 20 |
| Control styling | 15 / 20 | 17 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.
MaintainabilitySubscores
| Scoring dimension | k2.8high | Gemini 3.7 Flash Highdefault |
|---|---|---|
| Semantic clarity | 14 / 20 | 17 / 20 |
| Control-flow organization | 19 / 20 | 19 / 20 |
| Locality of changes | 15 / 20 | 14 / 20 |
| State and lifecycle | 17 / 20 | 18 / 20 |
| Implementation economy | 16 / 20 | 16 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.