Benchmark menu

Granite 4.2 8B

Other · Overall Models

Score · relative 0–100
9.9
Rank
63
Status
Partial 2/3
Rank change
Baseline
Last tested
2026-09-10
Settings tested
Missing Baseline

Why this result is partial: one or more bracket scores are missing; one or more documented settings are untested or ineligible; generation-quality evidence is missing; generation quality is below the publication threshold. The rank uses the available reasoning-setting results.

Scores by reasoning setting

Tested settingScoreResult statusDisplay group
Low7.7Tested and includedBalanced
Full12.1Tested and includedIntensive
Available settings and grouping

Available settings

Non-thinkingLowFull

Checked on 2026-09-03 · Provider documentation

How settings are grouped

  • Baseline: Non-thinking — available, not tested in the current results
  • Balanced: Low — tested and included
  • Intensive: Full — tested and included

Player program results

Full: 0% / 13% / 87% · n 8Low: 0% / 25% / 75% · n 8 Missing BaselineMany programs failed

Generation cost

Average estimated cost
$0.0040
Median estimated cost
$0.0028
Estimated range
$0.0013–$0.01
Cost data
24 combinations / 24 recorded runs
Observed total
$0.10
Price source
Provider-reported
Price list
Not recorded for this older data
Average output
13k tokens
Output range
2.8k–46k 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