Public Calibration
IFRS Reporting
Kaelum Bench · FMB-KNOW-ACC-IFRS-02
This view covers the concrete 60-task suite only. Its provisional 600-point score uses deterministic verification only. It exposes sanitized score, execution, token, and cost aggregates, with no prompts, responses, expected solutions, task IDs, provider generation IDs, keys, rationales, digests, or file paths.
IFRS Reporting · 60-task sub-benchmark
Calibration results
Sanitized lifecycle, coverage, score, token, and cost aggregates for FMB-KNOW-ACC-IFRS-02. Results are provisional and specific to the recorded model configuration.
- Sub-benchmark
- IFRS Reporting · FMB-KNOW-ACC-IFRS-02
- Models
- 7 calibration runs
- Coverage
- 60 tasks per model
- Deterministic
- 600 deterministic points
Execution detail
Model runs
Provisional deterministic results use deterministic verification only.
Provisional · Configuration-specific calibration · Single runs; no statistical ranking.
60 / 60
91.4%
548.7 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
93,694
$0.2066
60 / 60
91.9%
551.3 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
129,586
$0.6085
60 / 60
90.6%
543.3 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
140,832
$0.0292
60 / 60
90.7%
544.0 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
192,470
$0.1449
together · high reasoning
nemotron-3-ultra-550b-a55b — open run evidence
nvidia/nemotron-3-ultra-550b-a55b
60 / 60
89.7%
538.0 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
63,728
$0.0579
60 / 60
90.8%
544.7 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
187,444
$0.837
60 / 60
88.5%
531.0 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
69,462
$0.0497