# ArXivMath August 2026 without tools (ArXivMath Aug. 2026 (no tools))

> Final-answer research mathematics problems drawn from recent arXiv papers, including problems based on resolved or refuted conjectures.

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

- Category: [Mathematics](/math)
- Last updated: November 13, 2026

## About ArXivMath Aug. 2026 (no tools)

- Year: 2026
- Tasks: 57 recent research-mathematics problems
- Format: Final-answer accuracy
- Difficulty: Research mathematics
- Paper: [Claude Opus 5.5 System Card](https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf)

Section 8.9 reports four-attempt average accuracy on the distinct 57-problem August 2026 release at max effort without tools. It is not comparable to the June release and remains display-only.

ArXivMath Aug. 2026 (no tools) is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (2 models)

All 2 results on this page were reported by the labs that built the models.

| Rank | Model | Creator | Score | Who ran it |
|------|-------|---------|-------|-----------|
| 1 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 91.2% | Reported by Anthropic |
| 2 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | Anthropic | 86.8% | Reported by Anthropic |

## ArXivMath Aug. 2026 (tools)

Section 8.9 reports four-attempt average accuracy on the distinct 57-problem August 2026 release at max effort with tools. It remains separate from June and from MathArena's vendor-harness leaderboard.

Source: [Claude Opus 5.5 System Card](https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf)

| Rank | Model | Creator | Score | Who ran it |
|---|---|---|---|---|
| 1 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 96.9% | Reported by Anthropic |
| 2 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | Anthropic | 95.2% | Reported by Anthropic |

## ArXivMath Jun. 2026 (no tools)

Section 8.8 reports four-run average accuracy on the 49-problem June 2026 release at max effort without tools.

Source: [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf)

| Rank | Model | Creator | Score | Who ran it |
|---|---|---|---|---|
| 1 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | 90.8% | Reported by Anthropic |

## ArXivMath Jun. 2026 (tools)

Section 8.8 reports four-run average accuracy on the 49-problem June 2026 release at max effort with tools.

Source: [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf)

| Rank | Model | Creator | Score | Who ran it |
|---|---|---|---|---|
| 1 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | 91.3% | Reported by Anthropic |

## FAQ

### What does ArXivMath Aug. 2026 (no tools) measure?

Final-answer research mathematics problems drawn from recent arXiv papers, including problems based on resolved or refuted conjectures.

### Which model scores highest on ArXivMath Aug. 2026 (no tools)?

Claude Opus 5.5 by Anthropic currently leads with a score of 91.2% on ArXivMath Aug. 2026 (no tools).

### How many models are evaluated on ArXivMath Aug. 2026 (no tools)?

2 AI models have published results on ArXivMath Aug. 2026 (no tools) in the BenchLM catalog.

### Does ArXivMath Aug. 2026 (no tools) affect BenchLM's overall score?

Not directly. ArXivMath Aug. 2026 (no tools) is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on ArXivMath Aug. 2026 (no tools)

- [Claude Opus 5.5 vs Claude Sonnet 5.5](/compare/claude-opus-5-5-vs-claude-sonnet-5-5)