# International Mathematical Olympiad 2026 (IMO 2026)

> Proof-based olympiad performance on all six IMO 2026 problems.

Canonical page: https://benchlm.ai/benchmarks/imo2026

- Category: [Mathematics](/math)
- Last updated: September 8, 2026

## About IMO 2026

- Year: 2026
- Tasks: 6 proof-based problems
- Format: Official-style proof score
- Difficulty: International olympiad mathematics
- Paper: [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf)

Section 8.6 reports four independent no-tool solutions per problem. All 24 were accepted by a three-model panel, and human experts awarded one pre-specified solution per problem full credit.

IMO 2026 is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (2 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | 42/42 |
| 2 | [Apodex 1.1](/models/apodex-1-1) | Apodex | 31/42 |

## FAQ

### What does IMO 2026 measure?

Proof-based olympiad performance on all six IMO 2026 problems.

### Which model scores highest on IMO 2026?

Claude Opus 5 by Anthropic currently leads with a score of 42/42 on IMO 2026.

### How many models are evaluated on IMO 2026?

2 AI models have been evaluated on IMO 2026 on BenchLM.

### Does IMO 2026 affect BenchLM's overall score?

Not directly. IMO 2026 is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on IMO 2026

- [Claude Opus 5 vs Apodex 1.1](/compare/apodex-1-1-vs-claude-opus-5)