Skip to content

Benchmark

Finance Agent v2.1

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.

Models measured
1
Scores recorded
1
Sources
1
IQ weight
No weight published

Score distribution

58.8%
Mean
58.8%
Median
0%
Std dev
58.8%
10th percentile
58.8%
90th percentile
58.8%
Min

Leaderboard

#ModelScore
1MiniMax M3.1 FlashVals AI October 20 model evaluation · official MiniMax API · temperature 1 / top_p 0.95 / compute effort max · displayed uncertainty ±2.07 percentage points · output cap inconsistent across the page· Reported by Vals AI· via BenchBoard docs58.8%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.