Skip to content

Benchmark

CTI-REALM

Scores are percentages. Higher is better.

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

Score distribution

69.4%
Mean
69.4%
Median
0%
Std dev
69.4%
10th percentile
69.4%
90th percentile
69.4%
Min

Leaderboard

#ModelScore
1Fugu UltraFugu official headline evaluation· Reported by Sakana AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.69.4%

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.