Skip to content

Benchmark

FrontierScience Olympiad

Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.

Models measured
4
Scores recorded
5
Sources
2
IQ weight
No weight published

Score distribution

68.9%
Mean
74.8%
Median
12.5%
Std dev
44%
10th percentile
76%
90th percentile
44%
Min
44%76%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76%
2Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75%
3Hy3 (Deep Infra)· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.8%
4Hy3 (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.74.8%
5Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim44%

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.