Skip to content

Benchmark

SuperChem

Scores are percentages. Higher is better.

Models measured
5
Scores recorded
7
Sources
2
IQ weight
1.95

Score distribution

53.6%
Mean
56.6%
Median
15.9%
Std dev
54.9%
10th percentile
66.4%
90th percentile
16.2%
Min
16.2%66.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.95 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
1Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.4%
2Hy4 previewofficial model-card appendix· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.66.4%
3Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59.8%
4Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.6%
5Hy3 (Deep Infra)· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.9%
6Hy3 (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.54.9%
7Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim16.2%

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.