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

Claude Agent SDK · claude-haiku-4-5-20251001 · as published

anthropic

as published

Its score and figures

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

Its score and figures
rank in group1–12
Score84.9 pts81.9–86.8 pts
Pass rate98.6%95.7–100.0%98.6% · 69 of 69 graded
Efficiency43.935.0–47.8
cost1.1×
tokens2.3×
time0.39×
Coverage1/6
Runs69

73.9 + 2.6 + 0.8 + 7.6 = 84.9 (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

84.9 pts

IFEval: 98.6% · 69 of 69 graded · scored

cost
1.1× the typical spend per passing run1.1% 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($0.01–$0.02)30% went to the costliest 10% of attempts (7 of 69)
tokens
2.3× the typical spend per passing run1.3% of this setup's tokens here went to runs that did not pass or were not graded; efficiency does not price it35k per pass(32.1k–38.5k)20% went to the costliest 10% of attempts (7 of 69)cache split not recorded on 69 attempts
time
0.39× the typical spend per passing run0.9% of this setup's time here went to runs that did not pass or were not graded; efficiency does not price it11.9s per pass(9.2s–15.2s)36% 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.