Codex · gpt-5.4-mini · WebMCP
openai
with my setupWebMCPIts score and figures
Every figure the leaderboard's table prints for this setup.
| rank in group | 1–4 |
|---|---|
| Score | 80.8 pts76.9–84.3 pts |
| Pass rate | 98.0%93.8–100.0%98.0% · 49 of 50 graded |
| Efficiency | 29.123.2–38.7 |
| cost | 0.35× |
| tokens | 0.42× |
| time | 0.87× |
| Coverage | 1/6 |
| Runs | 50 |
73.5 + 3.2 + 0.7 + 3.4 = 80.8 (outcome + cost + tokens + time)
- pass rate on each benchmark's own grader
- cost
- tokens
- time
- not measured
- First run
- 2026-09-28
- Last run
- 2026-09-28
- did not finish (scored as a fail)
- 0
- Tasks with no grade
- 1
On each benchmark
Each benchmark it ran: its status, pass rate, spend and spend per pass. The studies behind them are its evidence, below.
WindTunnel
80.8 pts
WindTunnel: 98.0% · 49 of 50 graded · scored
- cost
- 0.35× the typical spend per passing run4.3% of this setup's cost here went to runs that did not pass or were not graded; efficiency does not price it$0.02 per pass($0.02–$0.02)16% went to the costliest 10% of attempts (5 of 49)
- tokens
- 0.42× the typical spend per passing run4.8% of this setup's tokens here went to runs that did not pass or were not graded; efficiency does not price it78.1k per pass(71.7k–85.5k)17% went to the costliest 10% of attempts (5 of 49)of which 87% cache reads and 13% fresh input
- time
- 0.87× the typical spend per passing run3.8% of this setup's time here went to runs that did not pass or were not graded; efficiency does not price it36.7s per pass(34.2s–39.7s)15% went to the costliest 10% of attempts (5 of 49)
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.