Model comparison
Selected 2 / 5See the differences. Choose what matters to you.
Available modelsSelected 2 / 5
Differences vs. Qwen3.8-Max · default
Score, cost & time differences
Current baseline · Qwen3.8-Max · default
57Maintainability
Compared with Qwen3.8-Max · default
- ERNIE 5.5 Flash Preview · Max
Maintainability: tiedComparable cost unavailableComparable time unavailable
Differences reflect these evaluation tasks. Cost and time cover the same dimension, not a typical conversation. Scoring & cost notes
| Metric | Qwen3.8-Max · default | ERNIE 5.5 Flash Preview · Max |
|---|---|---|
| Maintainability | Qwen3.8-Maxdefault 57 | ERNIE 5.5 Flash PreviewMax 57Tied |
| Overall | Qwen3.8-Maxdefault 64.30 | ERNIE 5.5 Flash PreviewMax 67.20+2.9 pts |
| Backend engineering | Qwen3.8-Maxdefault 65 | ERNIE 5.5 Flash PreviewMax 52−13 pts |
| Frontend interaction | Qwen3.8-Maxdefault 67 | ERNIE 5.5 Flash PreviewMax 52−15 pts |
| Knowledge & reasoning | Qwen3.8-Maxdefault 65 | ERNIE 5.5 Flash PreviewMax 90+25 pts |
| Visual aesthetics | Qwen3.8-Maxdefault 61 | ERNIE 5.5 Flash PreviewMax 66+5 pts |
Maintainability evaluation · Evaluation consumption, not a monthly subscription fee
Cost & time
Maintainability evaluation| Metric | Qwen3.8-Max · default | ERNIE 5.5 Flash Preview · Max |
|---|---|---|
| Cost | Qwen3.8-Maxdefault N/A | ERNIE 5.5 Flash PreviewMax N/A |
| Evaluation time | Qwen3.8-Maxdefault — | ERNIE 5.5 Flash PreviewMax — |
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 | Qwen3.8-Maxdefault | ERNIE 5.5 Flash PreviewMax |
|---|---|---|
| Contracts and boundaries | 12 / 20 | 7 / 20 |
| Retries and failures | 14 / 20 | 10 / 20 |
| CI and adversarial review | 12 / 20 | 14 / 20 |
| Transactions and consistency | 14 / 20 | 12 / 20 |
| Caching and regression | 13 / 20 | 9 / 20 |
Frontend interactionSubscores
| Scoring dimension | Qwen3.8-Maxdefault | ERNIE 5.5 Flash PreviewMax |
|---|---|---|
| Layout and adaptation | 18 / 20 | — |
| Interaction behavior | 13 / 20 | — |
| State continuity | 12 / 20 | — |
| Accessibility and feedback | 7 / 15 | 5 / 15 |
| State validation and regression | 17 / 25 | — |
Knowledge & reasoningSubscores
| Scoring dimension | Qwen3.8-Maxdefault | ERNIE 5.5 Flash PreviewMax |
|---|---|---|
| Mathematical reasoning | 15 / 15 | 15 / 15 |
| Computer science & AI | 10 / 15 | 10 / 15 |
| Science and engineering | 10 / 10 | 10 / 10 |
| Life sciences and medicine | 10 / 20 | 20 / 20 |
| Humanities and general knowledge | 20 / 40 | 35 / 40 |
Visual aestheticsSubscores
| Scoring dimension | Qwen3.8-Maxdefault | ERNIE 5.5 Flash PreviewMax |
|---|---|---|
| Composition | 19 / 20 | 18 / 20 |
| Spacing and alignment | 15 / 20 | 18 / 20 |
| Typography and expression | 16 / 20 | 16 / 20 |
| Color and surfaces | 19 / 20 | 19 / 20 |
| Control styling | 16 / 20 | 16 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.
MaintainabilitySubscores
| Scoring dimension | Qwen3.8-Maxdefault | ERNIE 5.5 Flash PreviewMax |
|---|---|---|
| Semantic clarity | 15 / 20 | 15 / 20 |
| Control-flow organization | 19 / 20 | 19 / 20 |
| Locality of changes | 16 / 20 | 15 / 20 |
| State and lifecycle | 17 / 20 | 17 / 20 |
| Implementation economy | 16 / 20 | 17 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.