Mathematics · Benchmark profile
A grade-school mathematical reasoning benchmark reported in DeepSeek-V4 base-model evaluations.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on Grade School Math 8K
DeepSeek V4 Pro Base leads at 92.6%, followed by DeepSeek V4 Flash Base (90.8%) and Soofi S 30B-A3B (86.1%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
3 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| DeepSeek V4 Pro Base | #1 | DeepSeek | 92.6% |
| DeepSeek V4 Flash Base | #2 | DeepSeek | 90.8% |
| Soofi S 30B-A3B | #3 | Soofi Project | 86.1% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | DeepSeek V4 Pro Base deepseek-v4-pro-base | DeepSeek | open | Estimated reference | 92.6% |
| #2 | DeepSeek V4 Flash Base deepseek-v4-flash-base | DeepSeek | open | Estimated reference | 90.8% |
| #3 | Soofi S 30B-A3B soofi-s-30b-a3b | Soofi Project | open | Estimated reference | 86.1% |
The top of this snapshot is led by DeepSeek V4 Pro Base at 92.6%; third place is 6.5 points behind. The top-3 spread is 6.5 points.
About Grade School Math 8K
A grade-school mathematical reasoning benchmark reported in DeepSeek-V4 base-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 grade-school mathematical reasoning benchmark reported in DeepSeek-V4 base-model evaluations.
DeepSeek V4 Pro Base by DeepSeek currently leads with 92.6%.
3 models in the LuminaBench cohort have a qualifying score on this benchmark.
Related
