Benchmark menu

Model results

GLM-5.2

See how GLM-5.2 performed, which reasoning settings were tested, how often it produced a working player program, and what those runs cost.

GLM-5.2

Provider: Zhipu

Rank
14
Status
Partial 3/3
Rank change
Baseline
Score
46.4
Last tested
2026-08-22
Settings tested
All settings tested

Why this result is partial: one or more documented settings are untested or ineligible; the official generation cohort is incomplete. The rank uses the available reasoning-setting results.

Scores by reasoning setting

Available settings

Reasoning disabledHighXHigh

Checked on 2026-07-21 · Provider documentation

Scores from tested settings

Tested settingScoreResult statusDisplay group
Reasoning disabled42.8Tested, not includedBaseline
Medium43.2Tested, not includedBalanced
XHigh53.3Tested and includedIntensive

How settings are grouped

  • Baseline: Reasoning disabled — available, not tested in the current results
  • Balanced: High — available, not tested in the current results
  • Intensive: XHigh — tested and included

Player program results

XHigh: 100% / 0% / 0% · n 2Medium: 0% / 100% / 0% · n 8Reasoning disabled: 56% / 44% / 0% · n 16 All settings testedMany programs needed repair

Generation cost

Average estimated cost
$0.05
Median estimated cost
$0.03
Estimated range
$0.01–$0.15
Cost data
17 combinations / 26 recorded runs
Observed total
$1.07
Price source
Provider-reported
Price list
Not recorded for this older data
Average output
91k tokens
Output range
28k–153k tokens
Samples
2

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