Skip to content

Benchmark

SRE-Bench · 4 Attempts

Scores are percentages. Higher is better.

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

Score distribution

84%
Mean
99.2%
Median
15.3%
Std dev
68.7%
10th percentile
99.2%
90th percentile
68.7%
Min
68.7%99.2%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT-6 Astrawithin 4 attempts· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.99.2%
2GPT-5.6 Solwithin 4 attempts· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.68.7%

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.