Skip to content

Benchmark

ChatGPT Answers Without Errors

Scores are percentages. Higher is better.

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

Score distribution

91%
Mean
93.9%
Median
3%
Std dev
88%
10th percentile
93.9%
90th percentile
88%
Min
88%93.9%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT 5.2with search · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93.9%
2GPT 5.2no search · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.88%

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.