# IMOAnswerBench leaderboard

Mathematics benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/math-imo-answer-bench

Every model the catalog carries a published IMOAnswerBench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Mathematics |
| Measure | Pass@1 math benchmark |
| Tasks | Advanced mathematical answer generation |
| Difficulty | Olympiad-level mathematics |
| Published by | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |

A challenging mathematical reasoning benchmark reported in DeepSeek-V4 model evaluations.

## IMOAnswerBench ranking

11 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 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [dots3-note Preview](https://modelscale.dev/models/dots3-note-preview) | Dots Studio | 90.9 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Qwen3.7 Max](https://modelscale.dev/models/qwen3-7-max) | Alibaba | 90.0 | Observed 2026-11-21 · source benchlm:models |
| 3 | [DeepSeek V4 Pro](https://modelscale.dev/models/deepseek-v4-pro) | DeepSeek | 89.8 | Observed 2026-11-21 · source benchlm:models |
| 3 | [DeepSeek V4 Pro 0813](https://modelscale.dev/models/deepseek-v4-pro-max) | DeepSeek | 89.8 | Last good 2026-11-18 · source benchlm:models |
| 5 | [DeepSeek V4 Flash 0731](https://modelscale.dev/models/deepseek-v4-flash-max) | DeepSeek | 88.4 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Qwen3.7 Plus](https://modelscale.dev/models/qwen3-7-plus) | Alibaba | 86.0 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Ling 3.0 Flash](https://modelscale.dev/models/ling-3-0-flash) | InclusionAI | 83.7 | Observed 2026-11-21 · source benchlm:models |
| 8 | [K-EXAONE 2.0](https://modelscale.dev/models/k-exaone-2-0) | LG AI Research | 78.6 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Spark-X2.6-4B](https://modelscale.dev/models/spark-x2-6-4b) | SparkLLM | 75.2 | Observed 2026-11-21 · source benchlm:models |
| 10 | [ZAYA1-8B](https://modelscale.dev/models/zaya1-8b) | Zyphra | 59.3 | Observed 2026-11-21 · source benchlm:models |
| 11 | [LongCat-Flash-Lite-Sparse](https://modelscale.dev/models/longcat-flash-lite-sparse) | Meituan | 49.4 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
