Public Calibration
Financial Analysis
Kaelum Bench · FMB-ANAL-FSA-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.
Financial Analysis · 60-task sub-benchmark
Calibration results
Sanitized lifecycle, coverage, score, token, and cost aggregates for FMB-ANAL-FSA-02. Results are provisional and specific to the recorded model configuration.
- Sub-benchmark
- Financial Analysis · FMB-ANAL-FSA-02
- Models
- 9 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
77.1%
462.7 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
233,536
$0.1829
60 / 60
52.2%
313.2 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
160,183
$0.0293
60 / 60
87.5%
525.3 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
292,869
$0.813
60 / 60
59.7%
358.4 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
207,754
$0.9979
60 / 60
91.9%
551.7 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
73,069
$0.0512
60 / 60
67.7%
406.3 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
115,169
$0.2823
together · high reasoning
nemotron-3-ultra-550b-a55b — open run evidence
nvidia/nemotron-3-ultra-550b-a55b
60 / 60
61.2%
367.0 / 600
59 valid answers
1 invalid JSON response
0 provider failures
69,620
$0.0692
60 / 60
77.8%
466.7 / 600
59 valid answers
1 invalid JSON response
0 provider failures
166,681
$0.9137
60 / 60
56.4%
338.5 / 600
60 valid answers
0 invalid JSON responses
0 provider failures
96,427
$0.221