Skip to content
kalanu
Theme
IFEval only · 12 setups · 1 of 6 compared benchmarks

Codex · gpt-5.4-mini · as published

openai

as published

Its score and figures

Every figure the leaderboard's table prints for this setup.

Its score and figures
rank in group1–12
Score88.5 pts86.1–89.9 pts
Pass rate100.0%≥ 94.8%100.0% · 69 of 69 graded
Efficiency53.944.5–59.8
cost0.37×
tokens0.83×
time0.85×
Coverage1/6
Runs69

75.0 + 7.9 + 2.1 + 3.4 ≈ 88.5 (outcome + cost + tokens + time)

  • pass rate on each benchmark's own grader
  • cost
  • tokens
  • time
  • not measured
First run
2026-10-03
Last run
2026-10-03
did not finish (scored as a fail)
0
Tasks with no grade
0

On each benchmark

Each benchmark it ran: its status, pass rate, spend and spend per pass. The studies behind them are its evidence, below.

IFEval

88.5 pts

IFEval: 100.0% · 69 of 69 graded · scored

cost
0.37× the typical spend per passing run0.0% of this setup's cost here went to runs that did not pass or were not graded; efficiency does not price it$0.01 per pass($0.0050–$0.01)39% went to the costliest 10% of attempts (7 of 69)
tokens
0.83× the typical spend per passing run0.0% of this setup's tokens here went to runs that did not pass or were not graded; efficiency does not price it14k per pass(11.2k–18.3k)31% went to the costliest 10% of attempts (7 of 69)of which 60% cache reads and 36% fresh input
time
0.85× the typical spend per passing run0.0% of this setup's time here went to runs that did not pass or were not graded; efficiency does not price it17.5s per pass(15.9s–19.2s)20% went to the costliest 10% of attempts (7 of 69)

Efficiency and spend per pass can order setups differently: efficiency compares the typical (median) passing run, task by task, while spend per pass averages every attempt, so a few very expensive runs, passing or not, count in full; and spend per pass also counts the attempts that failed or did not finish, and divides by the pass rate. A setup is called the most frugal only where both put it first and both separate it from every other setup.

Evidence

Every published study its runs come from.