Skip to main content

Benchmark profile

ArXivMath June 2026 with tools (ArXivMath Jun. 2026 (tools))

Final-answer research mathematics problems drawn from recent arXiv abstracts with tool access.

Data verified

Benchmark score on ArXivMath Jun. 2026 (tools) — July 24, 2026

BenchLM mirrors the published score view for ArXivMath Jun. 2026 (tools). Claude Opus 5 leads the public snapshot at 91.3%. BenchLM does not use these results to rank models overall.

1 modelMathCurrentDisplay onlyUpdated July 24, 2026

Benchmark score table (1 model)

Score
1
Claude Opus 5Anthropic · Closed
91.3%

About ArXivMath Jun. 2026 (tools)

Year

2026

Tasks

49 recent research-mathematics problems

Format

Final-answer accuracy with tools

Difficulty

Research mathematics

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

BenchLM freshness & provenance

Version

ArXivMath Jun. 2026 (tools) 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does ArXivMath Jun. 2026 (tools) measure?

Final-answer research mathematics problems drawn from recent arXiv abstracts with tool access.

Which model scores highest on ArXivMath Jun. 2026 (tools)?

Claude Opus 5 by Anthropic currently leads with a score of 91.3% on ArXivMath Jun. 2026 (tools).

How many models are evaluated on ArXivMath Jun. 2026 (tools)?

1 AI models have been evaluated on ArXivMath Jun. 2026 (tools) on BenchLM.

Last updated: July 24, 2026 · BenchLM version ArXivMath Jun. 2026 (tools) 2026