Skip to content

Benchmark

FrontierScience Research

Scores are percentages. Higher is better.

Models measured
8
Scores recorded
9
Sources
2
IQ weight
2.20

Score distribution

26.7%
Mean
28.3%
Median
10.2%
Std dev
21.3%
10th percentile
36.7%
90th percentile
3.3%
Min
3.3%38.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.20 for chat models, measured over 8 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim38.3%
2GPT-5.4 ProOpenAI GPT-5.4 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.36.7%
3Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim33.3%
4GPT 5.4OpenAI GPT-5.4 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.33%
5Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim28.3%
6GPT 5.2OpenAI GPT-5.4 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.25.2%
7Hy3 (Deep Infra)· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim21.3%
8Hy3 (Deep Infra)Hy3 official Benchmark Appendix · highest reasoning tier unless noted· Reported by Tencent Hunyuan· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.21.3%
9Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim3.3%

Data credits: Data by LLM Stats · 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.