Leaderboard bars
3 ranked models · higher is better
View accessible chart data
| Model | Rank | Provider | Score |
|---|---|---|---|
| GPT-5 | #1 | OpenAI | 99.4% |
| Grok 3 mini | #2 | xAI | 99.2% |
| o3 | #3 | OpenAI | 99.2% |
Loading benchmark header
Loading benchmark registry
Mathematics · Benchmark profile
A 500-problem competition-math subset from the MATH dataset spanning algebra, geometry, number theory, and related domains.
Data verified 15 July 2026 · Methodology 1.2.0
Benchmark score on MATH-500
GPT-5 leads at 99.4%, followed by Grok 3 mini (99.2%) and o3 (99.2%).
Visual analysis
Three views of the same sourced leaderboard: model placement, the score curve, and descriptive provider averages. These visuals never alter ranking calculations.
3 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| GPT-5 | #1 | OpenAI | 99.4% |
| Grok 3 mini | #2 | xAI | 99.2% |
| o3 | #3 | OpenAI | 99.2% |
Shows how quickly scores separate down the field
| Model | Rank | Provider | Score |
|---|---|---|---|
| GPT-5 | #1 | OpenAI | 99.4% |
| Grok 3 mini | #2 | xAI | 99.2% |
| o3 | #3 | OpenAI | 99.2% |
Average within the visible cohort · descriptive only
| Provider | Models | Average score |
|---|---|---|
| OpenAI | 2 | 99.3% |
| xAI | 1 | 99.2% |
One best score per model · higher is better
| Rank | Model | Provider | License | Score |
|---|---|---|---|---|
| #1 | GPT-5 gpt-5 | OpenAI | closed | 99.4% |
| #2 | Grok 3 mini grok-3-mini | xAI | closed | 99.2% |
| #3 | o3 o3 | OpenAI | closed | 99.2% |
The top of this snapshot is led by GPT-5 at 99.4%; third place is 0.20 points behind. The top-3 spread is 0.20 points.
About MATH-500
A 500-problem competition-math subset from the MATH dataset spanning algebra, geometry, number theory, and related domains. 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 500-problem competition-math subset from the MATH dataset spanning algebra, geometry, number theory, and related domains.
GPT-5 by OpenAI currently leads with 99.4%.
3 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