Model comparison
Selected 2 / 5See the differences. Choose what matters to you.
Available modelsSelected 2 / 5
Differences vs. claude-fable-5-1 · max
Score, cost & time differences
Current baseline · claude-fable-5-1 · max
87.40Overall
Compared with claude-fable-5-1 · max
- Claude Fable 5.2 · max
Overall: +6.6 ptsReference cost $81.98 ($55.83 more)Evaluation time 351m 33s (272m 26s more)
Differences reflect these evaluation tasks. Cost and time cover the same dimension, not a typical conversation. Scoring & cost notes
| Metric | claude-fable-5-1 · max | Claude Fable 5.2 · max |
|---|---|---|
| Overall | claude-fable-5-1max 87.40 | Claude Fable 5.2max 94.00+6.6 pts |
| Backend engineering | claude-fable-5-1max 83 | Claude Fable 5.2max 97+14 pts |
| Frontend interaction | claude-fable-5-1max 91 | Claude Fable 5.2max 96+5 pts |
| Knowledge & reasoning | claude-fable-5-1max 95 | Claude Fable 5.2max 100+5 pts |
| Visual aesthetics | claude-fable-5-1max 80 | Claude Fable 5.2max 83+3 pts |
| Maintainability | claude-fable-5-1max 68 | Claude Fable 5.2max 73+5 pts |
Complete evaluation · Evaluation consumption, not a monthly subscription fee
Cost & time
Complete evaluation| Metric | claude-fable-5-1 · max | Claude Fable 5.2 · max |
|---|---|---|
| Reference cost | claude-fable-5-1max $26.15 | Claude Fable 5.2max $81.98+$55.83 |
| Evaluation time | claude-fable-5-1max 79m 7s | Claude Fable 5.2max 351m 33s+344.3% |
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 | claude-fable-5-1max | Claude Fable 5.2max |
|---|---|---|
| Contracts and boundaries | 13 / 20 | 18 / 20 |
| Retries and failures | 20 / 20 | 20 / 20 |
| CI and adversarial review | 14 / 20 | 19 / 20 |
| Transactions and consistency | 19 / 20 | 20 / 20 |
| Caching and regression | 17 / 20 | 20 / 20 |
Frontend interactionSubscores
| Scoring dimension | claude-fable-5-1max | Claude Fable 5.2max |
|---|---|---|
| Layout and adaptation | 20 / 20 | 20 / 20 |
| Interaction behavior | 20 / 20 | 19 / 20 |
| State continuity | 15 / 20 | 20 / 20 |
| Accessibility and feedback | 13 / 15 | 15 / 15 |
| State validation and regression | 23 / 25 | 22 / 25 |
Knowledge & reasoningSubscores
| Scoring dimension | claude-fable-5-1max | Claude Fable 5.2max |
|---|---|---|
| Mathematical reasoning | 15 / 15 | 15 / 15 |
| Computer science & AI | 10 / 15 | 15 / 15 |
| Science and engineering | 10 / 10 | 10 / 10 |
| Life sciences and medicine | 20 / 20 | 20 / 20 |
| Humanities and general knowledge | 40 / 40 | 40 / 40 |
Visual aestheticsSubscores
| Scoring dimension | claude-fable-5-1max | Claude Fable 5.2max |
|---|---|---|
| Composition | 20 / 20 | 20 / 20 |
| Spacing and alignment | 18 / 20 | 19 / 20 |
| Typography and expression | 19 / 20 | 17 / 20 |
| Color and surfaces | 19 / 20 | 19 / 20 |
| Control styling | 17 / 20 | 19 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.
MaintainabilitySubscores
| Scoring dimension | claude-fable-5-1max | Claude Fable 5.2max |
|---|---|---|
| Semantic clarity | 16 / 20 | 18 / 20 |
| Control-flow organization | 20 / 20 | 20 / 20 |
| Locality of changes | 15 / 20 | 17 / 20 |
| State and lifecycle | 18 / 20 | 18 / 20 |
| Implementation economy | 19 / 20 | 17 / 20 |
Subscores retain their original scale; the axis score uses a consistent conversion.