Mathematics · Benchmark profile
A challenging mathematical reasoning benchmark reported in DeepSeek-V4 model evaluations.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on IMOAnswerBench
Qwen3.7-Max leads at 90%, followed by DeepSeek V4 Pro (Max) (89.8%) and DeepSeek V4 Flash (Max) (88.4%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
9 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Qwen3.7-Max | #1 | Alibaba Cloud | 90% |
| DeepSeek V4 Pro (Max) | #2 | DeepSeek | 89.8% |
| DeepSeek V4 Flash (Max) | #3 | DeepSeek | 88.4% |
| DeepSeek V4 Pro (High) | #4 | DeepSeek | 88% |
| Qwen3.7-Plus | #5 | Alibaba Cloud | 86% |
| DeepSeek V4 Flash (High) | #6 | DeepSeek | 85.1% |
| ZAYA1-8B | #7 | Zyphra | 59.3% |
| DeepSeek V4 Flash | #8 | DeepSeek | 41.9% |
| DeepSeek V4 Pro | #9 | DeepSeek | 35.3% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Qwen3.7-Max qwen3.7-max | Alibaba Cloud | — | Reference only | 90% |
| #2 | DeepSeek V4 Pro (Max) deepseek-v4-pro-max | DeepSeek | open | Estimated reference | 89.8% |
| #3 | DeepSeek V4 Flash (Max) deepseek-v4-flash-max | DeepSeek | open | Estimated reference | 88.4% |
| #4 | DeepSeek V4 Pro (High) deepseek-v4-pro-high | DeepSeek | open | Estimated reference | 88% |
| #5 | Qwen3.7-Plus qwen3.7-plus | Alibaba Cloud | — | Reference only | 86% |
| #6 | DeepSeek V4 Flash (High) deepseek-v4-flash-high | DeepSeek | open | Estimated reference | 85.1% |
| #7 | ZAYA1-8B zaya1-8b | Zyphra | open | Estimated reference | 59.3% |
| #8 | DeepSeek V4 Flash deepseek-v4-flash | DeepSeek | open | Estimated reference | 41.9% |
| #9 | DeepSeek V4 Pro deepseek-v4-pro | DeepSeek | open | Reference only | 35.3% |
The top of this snapshot is led by Qwen3.7-Max at 90%; third place is 1.6 points behind. The top-9 spread is 54.7 points.
About IMOAnswerBench
A challenging mathematical reasoning benchmark reported in DeepSeek-V4 model evaluations. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A challenging mathematical reasoning benchmark reported in DeepSeek-V4 model evaluations.
Qwen3.7-Max by Alibaba Cloud currently leads with 90%.
9 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
