Benchmark menu

Model results

Step 3.7 Flash

See how Step 3.7 Flash performed, which reasoning settings were tested, how often it produced a working player program, and what those runs cost.

Step 3.7 Flash

Provider: StepFun

Rank
41
Status
Partial 3/3
Rank change
Baseline
Score
30.8
Last tested
2026-08-19
Settings tested
All settings tested

Why this result is partial: generation quality is below the publication threshold. The rank uses the available reasoning-setting results.

Scores by reasoning setting

Available settings

LowMediumHigh

Checked on 2026-07-21 · Provider documentation

Scores from tested settings

Tested settingScoreResult statusDisplay group
Low31.0Tested and includedBaseline
Medium32.3Tested and includedBalanced
High29.1Tested and includedIntensive

How settings are grouped

  • Baseline: Low — tested and included
  • Balanced: Medium — tested and included
  • Intensive: High — tested and included

Player program results

High: 0% / 63% / 37% · n 8Medium: 0% / 50% / 50% · n 8Low: 38% / 12% / 50% · n 8 All settings testedMany programs needed repairMany programs failed

Generation cost

Average estimated cost
$0.04
Median estimated cost
$0.03
Estimated range
$0.0098–$0.11
Cost data
24 combinations / 24 recorded runs
Observed total
$1.00
Price source
Provider-reported
Price list
Not recorded for this older data
Average output
33k tokens
Output range
6.7k–93k tokens
Samples
24

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