Skip to content

Benchmark

SWE-Atlas · Refactoring

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

53.3%
Mean
53.3%
Median
0%
Std dev
53.3%
10th percentile
53.3%
90th percentile
53.3%
Min

Leaderboard

#ModelScore
1Hy4 previewofficial model-card appendix· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.53.3%

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.