Benchmark menu

Model results

GPT-5.6 Terra

See how GPT-5.6 Terra performed, which reasoning settings were tested, how often it produced a working player program, and what those runs cost.

GPT-5.6 Terra

Provider: OpenAI

Rank
13
Status
Complete 3/3
Rank change
Baseline
Score
47.6
Last tested
2026-08-05
Settings tested
All settings tested

Scores by reasoning setting

Available settings

NoneLowMediumHighXHighMax

Checked on 2026-07-21 · Provider documentation

Scores from tested settings

Tested settingScoreResult statusDisplay group
None41.9Tested and includedBaseline
Medium43.4Tested and includedBalanced
XHigh57.5Tested and includedIntensive

How settings are grouped

  • Baseline: None — tested and included
  • Balanced: Medium — tested and included
  • Intensive: XHigh — tested and included

Player program results

XHigh: 63% / 37% / 0% · n 8Medium: 63% / 37% / 0% · n 8None: 78% / 11% / 11% · n 9 All settings tested

Generation cost

Average estimated cost
$2.80
Median estimated cost
$0.16
Estimated range
$0.05–$12.14
Cost data
24 combinations / 25 recorded runs
Observed total
$67.27
Price source
Standard list-price estimate
Price list
boardgame-list-prices-2026-08-08
Average output
178k tokens
Output range
2.4k–806k tokens
Samples
25

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