# Claude Fable 5.2 / Search Capability Leaderboard

* Search Intelligence Score: **80.1** (#1 in Search Intelligence)
* Without search: 56.9 / Lift from search +23.2
* Cost per 1K tasks: $2,426 (#27 in Search Efficiency)
* Medals: Gold, Search Intelligence
* Evaluated: Nov 10, 2026
* Lab: Anthropic / Weights: Closed / Model id: claude-fable-5.2

## Accuracy by benchmark

| Suite | With search | Without search |
| ----- | ----------- | -------------- |
| DSQA  | 90.3        | 67.6           |
| HLE   | 69.0        | 71.0           |
| WISER | 81.0        | 32.0           |

## Compared with

| Model                                               | Score | Lift  | Cost per 1K tasks |
| --------------------------------------------------- | ----- | ----- | ----------------- |
| Claude Fable 5.2                                    | 80.1  | +23.2 | $2,426            |
| [Claude Opus 5.5](/leaderboard/claude-opus-5-5)     | 76.1  | +31.9 | $896              |
| [Claude Sonnet 5.5](/leaderboard/claude-sonnet-5-5) | 74.1  | +40.9 | $796              |
| [Claude Fable 5.1](/leaderboard/claude-fable-5-1)   | 73.4  | +26.5 | $1,762            |
| [Claude Opus 5](/leaderboard/claude-opus-5)         | 70.0  | +32.8 | $1,012            |

Leaderboard last updated Nov 12, 2026. Methodology: /leaderboard#methodology