Benchmark menu

Model results

GPT-5.4 Mini

See how GPT-5.4 Mini performed, which reasoning settings were tested, how often it produced a working player program, and what those runs cost.

GPT-5.4 Mini

Provider: OpenAI

Rank
25
Status
Partial 2/3
Rank change
Baseline
Score
38.7
Last tested
2026-08-05
Settings tested
Missing Intensive

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

NoneLowMediumHighXHigh

Checked on 2026-07-21 · Provider documentation

Scores from tested settings

Tested settingScoreResult statusDisplay group
None30.6Tested and includedBaseline
Medium46.8Tested and includedBalanced

How settings are grouped

  • Baseline: None — tested and included
  • Balanced: Medium — tested and included
  • Intensive: XHigh — available, not tested in the current results

Player program results

Medium: 88% / 12% / 0% · n 8None: 75% / 25% / 0% · n 8 Missing Intensive

Generation cost

Average estimated cost
$0.22
Median estimated cost
$0.17
Estimated range
$0.01–$1.50
Cost data
17 combinations / 18 recorded runs
Observed total
$5.17
Price source
Combined: Recorded attempt + Standard list-price estimate
Price list
boardgame-list-prices-2026-07-12 + boardgame-list-prices-2026-08-08
Average output
61k tokens
Output range
1.6k–384k tokens
Samples
18

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