Benchmark
Investment Banking Modeling Tasks
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 7
- Scores recorded
- 9
- Sources
- 1
- IQ weight
- 0.58
Score distribution
- 78.6%
- Mean
- 79.3%
- Median
- 8.2%
- Std dev
- 68.4%
- 10th percentile
- 88.5%
- 90th percentile
- 68.4%
- Min
This benchmark has a weight of 0.58 for chat models, measured over 7 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 Prointernal · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 88.6% |
| 2 | GPT 5.5internal · xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 88.5% |
| 3 | GPT 5.4OpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 87.3% |
| 4 | GPT-5.4 ProOpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 83.6% |
| 5 | GPT-5.3 CodexOpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 79.3% |
| 6 | GPT-5.2 Prointernal spreadsheet tasks · ChatGPT heavy· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 71.7% |
| 7 | GPT-5.2 ProOpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 71.7% |
| 8 | GPT 5.2internal spreadsheet tasks · ChatGPT heavy· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 68.4% |
| 9 | GPT 5.2OpenAI internal benchmark· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 68.4% |