Skip to content

Benchmark

Big Finance Bench

Scores are percentages. Higher is better.

Models measured
5
Scores recorded
8
Sources
2
IQ weight
0.37

Score distribution

46.6%
Mean
51%
Median
6.7%
Std dev
36%
10th percentile
53%
90th percentile
36%
Min
36%53%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.37 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53%
2GPT-5.6 SolOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.53%
3GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim51%
4GPT-5.6 TerraOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.51%
5GPT 5.5OpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.49%
6Claude Opus 4.8OpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.44%
7GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim36%
8GPT-5.6 LunaOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.36%

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. · Data by LLM Stats