Benchmark menu

Model results

DeepSeek V4 Flash

See how DeepSeek V4 Flash performed, which reasoning settings were tested, how often it produced a working player program, and what those runs cost.

DeepSeek V4 Flash

Provider: DeepSeek

Rank
34
Status
Partial 3/3
Rank change
Baseline
Score
33.3
Last tested
2026-08-05
Settings tested
All settings tested

Why this result is partial: one or more documented settings are untested or ineligible. 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 disabled29.2Tested and includedBaseline
Medium32.1Tested, not includedBalanced
XHigh38.7Tested and includedIntensive

How settings are grouped

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

Player program results

XHigh: 38% / 37% / 25% · n 8Medium: 63% / 25% / 12% · n 16Reasoning disabled: 63% / 25% / 12% · n 8 All settings testedMany programs failed

Generation cost

Average estimated cost
$0.0052
Median estimated cost
$0.0031
Estimated range
$0.0013–$0.02
Cost data
24 combinations / 32 recorded runs
Observed total
$0.15
Price source
Provider-reported
Price list
Not recorded for this older data
Average output
18k tokens
Output range
1.7k–82k 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