Skip to content

Benchmark

OpenAI Internal Research Debugging

Scores are percentages. Higher is better.

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

Score distribution

59.2%
Mean
67.8%
Median
8.8%
Std dev
50%
10th percentile
68.3%
90th percentile
50%
Min
50%68.3%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT-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.68.3%
2GPT-5.6 TerraOpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.67.8%
3GPT-5.6 LunaOpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.50.8%
4GPT 5.5OpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.50%

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.