Benchmark menu

Model results

Kimi K2.7 Code

See how Kimi K2.7 Code performed, which reasoning settings were tested, how often it produced a working player program, and what those runs cost.

Kimi K2.7 Code

Provider: Moonshot

Rank
18
Status
Partial 1/3
Rank change
Baseline
Score
42.4
Last tested
2026-08-05
Settings tested
Intensive not supported; Baseline not supported

Why this result is partial: one or more bracket scores are missing; three distinct provider settings are not documented; 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

Reasoning enabled

Checked on 2026-07-21 · Provider documentation

Scores from tested settings

Tested settingScoreResult statusDisplay group
Reasoning enabled42.4Tested and includedBalanced

How settings are grouped

  • Baseline: Not available for this model
  • Balanced: Reasoning enabled — tested and included
  • Intensive: Not available for this model

Player program results

Reasoning enabled: 0% / 75% / 25% · n 8 Intensive not supportedBaseline not supportedMany programs needed repairMany programs failed

Generation cost

Average estimated cost
$0.16
Median estimated cost
$0.14
Estimated range
$0.11–$0.23
Cost data
8 combinations / 8 recorded runs
Observed total
$1.28
Price source
Provider-reported
Price list
Not recorded for this older data
Average output
39k tokens
Output range
23k–56k tokens
Samples
8

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