Benchmark menu

Model results

Claude Fable 5

See how Claude Fable 5 performed, which reasoning settings were tested, how often it produced a working player program, and what those runs cost.

Claude Fable 5

Provider: Anthropic

Rank
1
Status
Partial 2/3
Rank change
Baseline
Score
74.7
Last tested
2026-08-05
Settings tested
Missing Baseline

Why this result is partial: one or more bracket scores are missing; one or more documented settings are untested or ineligible; generation-quality evidence is missing. The rank uses the available reasoning-setting results.

Scores by reasoning setting

Available settings

LowMediumHighXHighMax

Checked on 2026-07-21 · Provider documentation

Scores from tested settings

Tested settingScoreResult statusDisplay group
Medium66.1Tested and includedBalanced
XHigh83.3Tested and includedIntensive

How settings are grouped

  • Baseline: Low — available, not tested in the current results
  • Balanced: Medium — tested and included
  • Intensive: XHigh — tested and included

Player program results

XHigh: 63% / 37% / 0% · n 8Medium: 88% / 0% / 12% · n 8 Missing Baseline

Generation cost

Average estimated cost
$1.04
Median estimated cost
$0.88
Estimated range
$0.33–$1.92
Cost data
16 combinations / 16 recorded runs
Observed total
$16.70
Price source
Standard list-price estimate
Price list
boardgame-list-prices-2026-08-08
Average output
18k tokens
Output range
4.3k–36k tokens
Samples
16

Estimated cost gives equal weight to each model, game, and reasoning-setting combination.

Test setup

  • Combines this model's tested reasoning settings
  • Uses the standard GameBench player-program prompt