Skip to content

Benchmark

GDP.pdf · OpenAI chart score

Scores are percentages. Higher is better.

Models and systems measured
4
Scores recorded
20
Sources
1
IQ weight
No weight published

Score distribution

28.2%
Mean
28.8%
Median
3%
Std dev
24.8%
10th percentile
31.8%
90th percentile
21.8%
Min
21.8%32.2%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#Model or systemScore
1GPT-6 AstraGDP.pdf professional PDF tasks · OpenAI release chart · xhigh reasoning · displayed cost $1.91/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.32.2%
2GPT-6.1 SolGDP.pdf professional PDF tasks · OpenAI release chart · high reasoning · displayed cost $0.35/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.32%
3GPT-6.1 SolGDP.pdf professional PDF tasks · OpenAI release chart · xhigh reasoning · displayed cost $0.37/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.31.8%
4GPT-6 AstraGDP.pdf professional PDF tasks · OpenAI release chart · high reasoning · displayed cost $1.79/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.31%
5GPT-6 AstraGDP.pdf professional PDF tasks · OpenAI release chart · max reasoning · displayed cost $2.08/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.31%
6GPT-6.1 SolGDP.pdf professional PDF tasks · OpenAI release chart · max reasoning · displayed cost $0.42/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.31%
7GPT-6 AstraGDP.pdf professional PDF tasks · OpenAI release chart · low reasoning · displayed cost $1.70/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.30.4%
8GPT-6 AstraGDP.pdf professional PDF tasks · OpenAI release chart · medium reasoning · displayed cost $1.72/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.30.4%
9GPT-6.1 SolGDP.pdf professional PDF tasks · OpenAI release chart · medium reasoning · displayed cost $0.34/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.30%
10GPT-6 SolGDP.pdf professional PDF tasks · OpenAI release chart · high reasoning · displayed cost $0.35/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.28%
11GPT-6.1 SolGDP.pdf professional PDF tasks · OpenAI release chart · low reasoning · displayed cost $0.33/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.27%
12GPT-6 SolGDP.pdf professional PDF tasks · OpenAI release chart · medium reasoning · displayed cost $0.34/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.25.4%
13GPT-6 SolGDP.pdf professional PDF tasks · OpenAI release chart · max reasoning · displayed cost $0.43/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.24.8%
14GPT-6 SolGDP.pdf professional PDF tasks · OpenAI release chart · xhigh reasoning · displayed cost $0.37/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.23.8%
15GPT-6 SolGDP.pdf professional PDF tasks · OpenAI release chart · low reasoning · displayed cost $0.33/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.21.8%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Claude Opus 5.5 with fallbacks (OpenAI chart label)GDP.pdf professional PDF tasks · OpenAI release chart · high reasoning · displayed cost $0.83/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.28.8%
Claude Opus 5.5 with fallbacks (OpenAI chart label)GDP.pdf professional PDF tasks · OpenAI release chart · low reasoning · displayed cost $0.76/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.25.6%
Claude Opus 5.5 with fallbacks (OpenAI chart label)GDP.pdf professional PDF tasks · OpenAI release chart · max reasoning · displayed cost $1.55/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.26.2%
Claude Opus 5.5 with fallbacks (OpenAI chart label)GDP.pdf professional PDF tasks · OpenAI release chart · medium reasoning · displayed cost $0.80/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.25.6%
Claude Opus 5.5 with fallbacks (OpenAI chart label)GDP.pdf professional PDF tasks · OpenAI release chart · xhigh reasoning · displayed cost $0.96/task· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.26.6%

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.