Model comparison
Selected 2 / 5See the differences. Choose what matters to you.
Available modelsSelected 2 / 5
Differences vs. GPT-6.1 Sol · max
Score, cost & time differences
Current baseline · GPT-6.1 Sol · max
63.8Overall
Compared with GPT-6.1 Sol · max
- GPT-6 Sol · max
Overall: −6.8 ptsCost $31.37 ($18.69 more)Evaluation time 149m 41s (34m 42s less)
Differences reflect these evaluation tasks. Cost and time cover the same dimension, not a typical conversation. Scoring & cost notes
| Metric | GPT-6.1 Sol · max | GPT-6 Sol · max |
|---|---|---|
| Overall | GPT-6.1 Solmax 63.8 | GPT-6 Solmax 57.0−6.8 pts |
| Backend engineering | GPT-6.1 Solmax 59.4 | GPT-6 Solmax 46.7−12.8 pts |
| Visual aesthetics | GPT-6.1 Solmax 34.0 | GPT-6 Solmax 25.0−9 pts |
| Knowledge & reasoning | GPT-6.1 Solmax 85.0 | GPT-6 Solmax 70.0−15 pts |
| Frontend engineering | GPT-6.1 Solmax 83.5 | GPT-6 Solmax 76.6−6.9 pts |
| Maintainability | GPT-6.1 Solmax 47.0 | GPT-6 Solmax 68.0+21 pts |
Complete evaluation · Evaluation consumption, not a monthly subscription fee
Cost & time
Complete evaluation| Metric | GPT-6.1 Sol · max | GPT-6 Sol · max |
|---|---|---|
| Cost | GPT-6.1 Solmax $12.68 | GPT-6 Solmax $31.37+$18.69 |
| Evaluation time | GPT-6.1 Solmax 184m 23s | GPT-6 Solmax 149m 41s−18.8% |
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 | GPT-6.1 Solmax | GPT-6 Solmax |
|---|---|---|
| Contracts and exceptional boundaries | 71.2 / 100.0 | 57.9 / 100.0 |
| State consistency and persistence | 84.1 / 100.0 | 71.9 / 100.0 |
| Dependencies, scheduling and resources | 95.3 / 100.0 | 76.9 / 100.0 |
| Queries and data transformations | 14.3 / 100.0 | 4.6 / 100.0 |
Visual aestheticsSubscores
| Scoring dimension | GPT-6.1 Solmax | GPT-6 Solmax |
|---|---|---|
| Content hierarchy and readability | 16.0 / 20.0 | 15.0 / 20.0 |
| Spatial organization and information capacity | 15.0 / 20.0 | 15.0 / 20.0 |
| Responsive adaptation and layout | 14.0 / 20.0 | 15.0 / 20.0 |
| Control craft and visual distinction | 13.0 / 15.0 | 13.0 / 15.0 |
| Editing context and status expression | 12.0 / 25.0 | 5.0 / 25.0 |
Subscores retain their original scale; the axis score uses a consistent conversion.
Knowledge & reasoningSubscores
| Scoring dimension | GPT-6.1 Solmax | GPT-6 Solmax |
|---|---|---|
| Mathematical reasoning | 15.0 / 15.0 | 10.0 / 15.0 |
| Computer science & AI | 15.0 / 15.0 | 10.0 / 15.0 |
| Science and engineering | 10.0 / 10.0 | 10.0 / 10.0 |
| Life sciences and medicine | 20.0 / 20.0 | 15.0 / 20.0 |
| Humanities and general knowledge | 25.0 / 40.0 | 25.0 / 40.0 |
Frontend engineeringSubscores
| Scoring dimension | GPT-6.1 Solmax | GPT-6 Solmax |
|---|---|---|
| Environment adaptation | 7.5 / 10.0 | 7.5 / 10.0 |
| Interaction control | 9.4 / 17.0 | 9.4 / 17.0 |
| Intent preservation | 16.5 / 17.0 | 13.5 / 17.0 |
| State consistency | 17.0 / 17.0 | 17.0 / 17.0 |
| Fault recovery | 10.3 / 12.0 | 10.3 / 12.0 |
| Task continuity | 7.4 / 9.0 | 4.7 / 9.0 |
| Operability | 9.3 / 12.0 | 8.2 / 12.0 |
| Understandable feedback | 6.0 / 6.0 | 6.0 / 6.0 |
MaintainabilitySubscores
| Scoring dimension | GPT-6.1 Solmax | GPT-6 Solmax |
|---|---|---|
| Code comprehension and responsibility | 21.0 / 25.0 | 24.0 / 25.0 |
| Change isolation and reuse | 20.0 / 25.0 | 22.0 / 25.0 |
| State and lifecycle | 17.0 / 20.0 | 18.0 / 20.0 |
| Complexity and necessary mechanisms | 13.0 / 20.0 | 17.0 / 20.0 |
| Diagnosis and behavioral verification | 6.5 / 10.0 | 7.0 / 10.0 |
Subscores retain their original scale; the axis score uses a consistent conversion.