SCIENCE UNDER AUTOMATION

FrontierMath Tier 4 v2 / official CSV

Official export: gpt-6.1-sol_max mean_score 1.0, run HgAUm5zxrWbkfYUdeJMGzL, started 2026-09-29.

What this result supports

Corrected June 2026 benchmark; 43 Tier-4 problems, two public, evaluations normally private. Exact per-run denominator and full logs absent in CSV; numeric answers are not research-proof verification.

Evidence record: independent_benchmark. Checked: 2026-10-20.

Read the primary source ↗

Where this evidence is used

Mathematics

• Understand a formalizable problem: FrontierMath supplies the problem; run-level details remain incomplete.
• Find a correct answer: Current Tier-4 results show strong answer finding under tool and token budgets.
• Supply a complete verified proof: Numerical answer grading does not test proof completeness.