Skip to content

Benchmark

Sierra τ³-Banking · Voice

Scores are percentages. Higher is better.

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

Score distribution

35.1%
Mean
35.1%
Median
0%
Std dev
35.1%
10th percentile
35.1%
90th percentile
35.1%
Min

Leaderboard

#ModelScore
1Gemini 3.8 Live Extended Thinkinghigh thinking · Gemini API · pass@1 · Sierra τ³-Banking· Reported by Google DeepMind, Google· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.35.1%

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.