Mathematics · Benchmark profile
United States of America Mathematical Olympiad 2026 problems used as an expert math evaluation.
Data verified 15 July 2026 · Methodology 1.2.0
Benchmark score on USAMO 2026
Claude Mythos 5 leads at 99.8%, followed by Claude Opus 4.8 (96.7%) and MiniMax M3 (85.7%).
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 |
|---|---|---|---|
| Claude Mythos 5 | #1 | Anthropic | 99.8% |
| Claude Opus 4.8 | #2 | Anthropic | 96.7% |
| MiniMax M3 | #3 | MiniMax | 85.7% |
Shows how quickly scores separate down the field
| Model | Rank | Provider | Score |
|---|---|---|---|
| Claude Mythos 5 | #1 | Anthropic | 99.8% |
| Claude Opus 4.8 | #2 | Anthropic | 96.7% |
| MiniMax M3 | #3 | MiniMax | 85.7% |
Average within the visible cohort · descriptive only
| Provider | Models | Average score |
|---|---|---|
| Anthropic | 2 | 98.3% |
| MiniMax | 1 | 85.7% |
One best score per model · higher is better
| Rank | Model | Provider | License | Score |
|---|---|---|---|---|
| #1 | Claude Mythos 5 claude-mythos-5 | Anthropic | closed | 99.8% |
| #2 | Claude Opus 4.8 claude-opus-4-8 | Anthropic | closed | 96.7% |
| #3 | MiniMax M3 MiniMax-M3 | MiniMax | — | 85.7% |
The top of this snapshot is led by Claude Mythos 5 at 99.8%; third place is 14.1 points behind. The top-3 spread is 14.1 points.
About USAMO 2026
United States of America Mathematical Olympiad 2026 problems used as an expert math evaluation. 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
United States of America Mathematical Olympiad 2026 problems used as an expert math evaluation.
Claude Mythos 5 by Anthropic currently leads with 99.8%.
3 models in the LuminaBench cohort have a qualifying score on this benchmark.
Yes. This family is ranking-weighted at 2.3% of its capability category. Claude Mythos 5 is overall #1.
Related
