Mathematics benchmark
IMOAnswerBench leaderboard
Every model the catalog carries a published IMOAnswerBench value for, ranked by that value.
CategoryMathematics
MeasurePass@1 math benchmark
TasksAdvanced mathematical answer generation
DifficultyOlympiad-level mathematics
Published byDeepSeek-V4 Technical Report
A challenging mathematical reasoning benchmark reported in DeepSeek-V4 model evaluations.
IMOAnswerBench ranking
9 models with a published IMOAnswerBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Pass@1 math benchmark |
|---|---|---|---|
| 1 | DSdots3-note Preview | Dots Studio | 90.9 |
| 2 |  Qwen3.7 Max | Alibaba | 90.0 |
| 3 |  DeepSeek V4 Pro 0813 | DeepSeek | 89.8 |
| 4 | DeepSeek V4 Flash 0731 | DeepSeek | 88.4 |
| 5 | Qwen3.7 Plus | Alibaba | 86.0 |
| 6 |  Ling 3.0 Flash | InclusionAI | 83.7 |
| 7 |  K-EXAONE 2.0 | LG AI Research | 78.6 |
| 8 | ZYZAYA1-8B | Zyphra | 59.3 |
| 9 |  LongCat-Flash-Lite-Sparse | Meituan | 49.4 |
Evidence key: Observed
Rows are ordered by the value DeepSeek-V4 Technical Report published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.