Skip to content

Benchmark

Management Consulting Tasks

Scores are percentages. Higher is better.

Models measured
7
Scores recorded
7
Sources
1
IQ weight
No weight published

Score distribution

32.5%
Mean
35.4%
Median
8.7%
Std dev
31.3%
10th percentile
37.2%
90th percentile
13.2%
Min
13.2%43.2%
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.43.2%
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.37.2%
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.35.5%
4GPT-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.35.4%
5Claude Opus 4.8OpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.31.6%
6GPT 5.5OpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.31.3%
7Gemini 3.1 Pro PreviewOpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.13.2%

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.