Kaelum Bench

60-task benchmark

HGB Reporting

FMB-KNOW-ACC-HGB-02 · Public calibration

HGB financial reporting and statement presentation.

What this benchmark tests

Published benchmark scope without claiming separate competency scores.

  • Bookkeeping, inventory, and preparation duties
  • Recognition choices and prohibitions
  • Initial and subsequent measurement
  • HGB statement error reconstruction

Benchmark shape

Only definition and published scoring properties are shown.

Difficulty
12 basic · 30 intermediate · 18 advanced
Comparison
Configuration-specific
Available points
600 available points
AI judge
Not used

Published model runs

All 14 models

Select a row to inspect its benchmark-specific evidence.

  • Recorded cost & tokens
    Cost
    $0.9205
    Tokens
    166,578
  • Recorded cost & tokens
    Cost
    $0.2461
    Tokens
    101,528
  • Recorded cost & tokens
    Cost
    $0.2722
    Tokens
    70,087
  • Recorded cost & tokens
    Cost
    $1.10
    Tokens
    377,761
  • Recorded cost & tokens
    Cost
    $0.1892
    Tokens
    240,228
  • Recorded cost & tokens
    Cost
    $0.053
    Tokens
    74,392
  • Recorded cost & tokens
    Cost
    $0.7239
    Tokens
    118,008
  • Recorded cost & tokens
    Cost
    $0.0416
    Tokens
    68,537
  • Recorded cost & tokens
    Cost
    $1.08
    Tokens
    151,493
  • Recorded cost & tokens
    Cost
    $2.12
    Tokens
    319,978
  • Recorded cost & tokens
    Cost
    $0.0483
    Tokens
    214,446
  • Recorded cost & tokens
    Cost
    $0.1038
    Tokens
    65,640
  • Recorded cost & tokens
    Cost
    $0.0147
    Tokens
    60,434
  • Recorded cost & tokens
    Cost
    $0.0756
    Tokens
    72,451

Campaign evidence summary

Completed runs
14
Total recorded cost
$6.98
Total tokens
2,101,561
Valid outputs
839 / 840