Mathematics · Benchmark profile
Final-answer research mathematics problems drawn from recent arXiv abstracts with tool access.
Data verified 27 Jul 2026 · Methodology 1.7.0
Benchmark score on ArXivMath June 2026 with tools
Claude Opus 5 leads at 91.3%.
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
1 ranked models · higher is better · labels show rank and score
| Model | Rank | Provider | Score |
|---|---|---|---|
| Claude Opus 5 | #1 | Anthropic | 91.3% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Claude Opus 5 claude-opus-5 | Anthropic | closed | Estimated reference | 91.3% |
About ArXivMath June 2026 with tools
Final-answer research mathematics problems drawn from recent arXiv abstracts with tool access. 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
Final-answer research mathematics problems drawn from recent arXiv abstracts with tool access.
Claude Opus 5 by Anthropic currently leads with 91.3%.
1 model 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
