Skip to content

Benchmark

AutoResearch · Validation BPB

Lower scores are better.

Models measured
1
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

0.976
Mean
0.977
Median
0.001
Std dev
0.975
10th percentile
0.977
90th percentile
0.975
Min
0.9750.977
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Fugu UltraFugu technical report · best single seed· Reported by Sakana AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.0.975
2Fugu UltraFugu technical report · mean best validation · ±0.0019· Reported by Sakana AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.0.977

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.