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 verifiedBenchmark 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.
Benchmark score table (1 model)
ScoreAbout 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
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.