Model comparison
Compare models or reasoning efforts by score, evaluation time and estimated cost.
Available modelsSelected 2 / 3
Measured results
Differences are relative to the first column
gpt-5.6-terraBackend +12 pts · Reasoning −5 pts
| Metric | claude-haiku-5-5 · xhigh | gpt-5.6-terra · max |
|---|---|---|
| Overall | 65.65 | 65.90+0.25 pts |
| Backend engineering | 69 | 81+12 pts |
| Frontend interaction | 78 | 76−2 pts |
| Knowledge & reasoning | 60 | 55−5 pts |
| Visual aesthetics | 59 | 61+2 pts |
| Maintainability | 64 | 61−3 pts |
Cost & time
Complete evaluation| Metric | claude-haiku-5-5 · xhigh | gpt-5.6-terra · max |
|---|---|---|
| Reference cost | $0.21 | $1.94+$1.73 |
| Evaluation time | 27m 38s | 133m 2s+381.5% |
Dimension breakdown
Expand to inspect each subaxis.
Backend engineeringSubscores
| Scoring dimension | claude-haiku-5-5xhigh | gpt-5.6-terramax |
|---|---|---|
| Contracts and boundaries | 15 / 20 | 17 / 20 |
| Retries and failures | 15 / 20 | 17 / 20 |
| CI and adversarial review | 12 / 20 | 12 / 20 |
| Transactions and consistency | 12 / 20 | 17 / 20 |
| Caching and regression | 15 / 20 | 18 / 20 |
Frontend interactionSubscores
| Scoring dimension | claude-haiku-5-5xhigh | gpt-5.6-terramax |
|---|---|---|
| Layout and adaptation | 18 / 20 | 18 / 20 |
| Interaction behavior | 20 / 20 | 17 / 20 |
| State continuity | 15 / 20 | 10 / 20 |
| Accessibility and feedback | 10 / 15 | 12 / 15 |
| State validation and regression | 15 / 25 | 19 / 25 |
Knowledge & reasoningSubscores
| Scoring dimension | claude-haiku-5-5xhigh | gpt-5.6-terramax |
|---|---|---|
| Mathematical reasoning | 10 / 15 | 10 / 15 |
| Computer science & AI | 5 / 15 | 10 / 15 |
| Science and engineering | 5 / 10 | 0 / 10 |
| Life sciences and medicine | 15 / 20 | 15 / 20 |
| Humanities and general knowledge | 25 / 40 | 20 / 40 |
Visual aestheticsSubscores
| Scoring dimension | claude-haiku-5-5xhigh | gpt-5.6-terramax |
|---|---|---|
| Composition | 19 / 20 | 18 / 20 |
| Spacing and alignment | 16 / 20 | 16 / 20 |
| Typography and expression | 16 / 20 | 17 / 20 |
| Color and surfaces | 18 / 20 | 18 / 20 |
| Control styling | 15 / 20 | 16 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.
MaintainabilitySubscores
| Scoring dimension | claude-haiku-5-5xhigh | gpt-5.6-terramax |
|---|---|---|
| Semantic clarity | 15 / 20 | 15 / 20 |
| Control-flow organization | 20 / 20 | 20 / 20 |
| Locality of changes | 17 / 20 | 16 / 20 |
| State and lifecycle | 18 / 20 | 18 / 20 |
| Implementation economy | 16 / 20 | 16 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.