minif2f-v1

MIT
lean-math

supplier yangky11 · mathlib f897ebcf72cd16f89ab4577d0c826cd14afaafc7 · cohort benchmark

Run the whole suite:./swarm/run.sh --goal minif2f-v1-suite

Summary

Benchmarks
244
Proved
4/244
Credited / glue
212 / 32
Runs
12
Pass rate
33%
Best solve
4m 6s
Median solve
4m 20s
Worst solve
36m 19s

Accuracy is the per-run success rate; every proved run is kernel-verified (Gate A). pass@k arrives with per-attempt telemetry (SPEC-092-A).

Benchmarks (244)

Runs (12)

GoalContributorModelDate (UTC)TimeResultVerification
aime-1990-p2cgbarlowclaude/fable2026-07-29 21:114m 25s
pass
kernel
aime-1988-p3cgbarlowclaude/fable2026-07-29 21:068m 29s
failed
aime-1984-p5cgbarlowclaude/fable2026-07-29 20:5435m 15s
failed
amc12a-2008-p15cgbarlowclaude/fable2026-07-29 06:4836m 19s
pass
kernel
amc12a-2003-p24cgbarlowclaude/fable2026-07-29 05:204m 6s
pass
kernel
aime-1983-p9cgbarlowclaude/fable2026-07-29 02:094m 15s
pass
kernel
aime-1983-p9cgbarlowclaude/opus2026-07-01 04:1524m 22s
failed
aime-1983-p9cgbarlowclaude/opus2026-07-01 03:496m 13s
failed
aime-1983-p9cgbarlowclaude/opus2026-07-01 03:4216m 58s
failed
aime-1983-p9cgbarlowclaude/opus2026-07-01 00:0524m 53s
failed
aime-1983-p9cgbarlowclaude/opus2026-06-30 20:5516m 55s
decomposed
algebra-2complexrootspoly-xsqp49eqxp7itxpn7icgbarlowclaude/opus2026-06-30 20:4914m
failed