Skip to content

Benchmark

OpenAI Internal Database Migration Tasks

Scores are percentages. Higher is better.

Models measured
4
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

53.7%
Mean
57.8%
Median
8%
Std dev
42.7%
10th percentile
63.9%
90th percentile
42.7%
Min
42.7%63.9%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT-6 AstraOpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.9%
2Claude Fable 5.1OpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.57.8%
3Claude Fable 5OpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.50.3%
4GPT-5.6 SolOpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.42.7%

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.