Answer prose round 1: 1 🔴, 3 🟡 (0 misread); compare against Opus 5.5 at medium, name the old steps and the stopping rungs, and leave the call stamp to the settling chunk
CI / tests (pull_request) Successful in 2m54s
CI / tests (pull_request) Successful in 2m54s
This commit was merged in pull request #534.
This commit is contained in:
+1
-1
@@ -532,7 +532,7 @@ A project's rung is its model's cheapest rung, which for Opus 5.5 is its default
|
||||
|
||||
2026-11-11, lilleman approved the rungs for Fable 5.2 from the index read that day. Its score and cost per task, for each effort from low to max: Sonnet 5.5 26 $0.51, 31 $0.78, 42 $1.64, 50 $4.09, 55 $10.02; Opus 5.5 35 $0.98, 48 $2.45, 52 $3.46, 57 $6.05, 59 $10.04; Fable 5.2 54 $3.10, 56 $3.80, 62 $9.08, 62 $14.83, 65 $26.54. The cut drops Opus 5.5 at high, since Fable 5.2 at low scores more for less; Opus 5.5 at max, since Fable 5.2 at high scores more for less; and Fable 5.2 at xhigh, which ties Fable 5.2 at high at a higher cost. Sonnet 5.5 at high stays the bottom rung, as the 2026-10-29 note chose. With Haiku 5.5 off, the cut alone would also keep Sonnet 5.5 at low and medium and Opus 5.5 at low, below it. On an Opus 5.5 project, an L 4 worker, an E + I 5 review and a worker's first escalation now run on Fable 5.2 at low, where they ran on Opus 5.5 at high; E + I 8 runs on Fable 5.2 at high, where it ran on Fable 5.1 at max. Three steps land on a rung the index scores lower than before: E + I 6 on Fable 5.2 at medium, 56 against Opus 5.5 at xhigh's 57; E + I 7 on Opus 5.5 at xhigh, 57 against Opus 5.5 at max's 59; and an L 3 worker's escalation stops, without lilleman's yes, at Fable 5.2 at medium, where it stopped at Opus 5.5 at xhigh. On a Sonnet 5.5 project, E + I 6 runs on Fable 5.2 at low, 54 against Opus 5.5 at high's 52; E + I 7 on Fable 5.2 at medium, 56 against Opus 5.5 at xhigh's 57; and E + I 8 on Opus 5.5 at xhigh, 57 against Opus 5.5 at max's 59. Fable 5.2 at max, on top, is reached only one rung up from Fable 5.2 at high, as by a reviewer's rerun. A Fable 5.2 project's rung is Fable 5.2 at low, so its L 1 and L 2 workers run on Opus 5.5 at medium.
|
||||
|
||||
2026-11-14, lilleman, settling the routing calls of the figures measured at 2026-11-14T00:59:50Z: L 3 steps one rung up and L 4 two up, in every project and for delegated subagents too, so the steps stay one table. On an Opus 5.5 project an L 3 worker or subagent runs on Fable 5.2 at low, and an L 4 one on Fable 5.2 at medium. The escalation limits, counted from the rung an item picks, rise with it. Until the chunk that changes `bin/model_routing/ladder.py` merges, the steps above hold. That chunk then appends a `Reset`. The calls came from 276 chunks finished since the 2026-10-29 reset. Chunks started on Opus 5.5 at medium, 79 of them, took a mean 0.8 review rounds past each pass's first, 0.3 unfinished verdicts and 0.2 later fixes. Chunks started on Fable 5.2 at low, 5 of them, took 0.4, 0.0 and 0.0. On an Opus 5.5 project only L 4 items start there, so Fable 5.2 did better on harder items. Two things weaken the evidence: 5 chunks is the fewest a call allows, and the Opus 5.5 figures include chunks from before Fable 5.2 joined the ladder. lilleman accepted about three times the cost per task for most chunks ($3.10 against $0.98 on the 2026-11-11 index) to get fewer rounds and fewer unfinished verdicts (goal 1.4).
|
||||
2026-11-14, lilleman ruled that L 3 is to step one rung up and L 4 two up, in every project and for delegated subagents. The steps stated above, L 3 none and L 4 one up, hold until `bin/model_routing/ladder.py` changes. Then, on an Opus 5.5 project, an L 3 worker or subagent runs on Fable 5.2 at low, and an escalation stops without lilleman's yes at Opus 5.5 at xhigh. An L 4 one runs on Fable 5.2 at medium, and stops at Fable 5.2 at high. The ruling settles the two calls of the routing figures measured at 2026-11-14T00:59:50Z, which were not yet in `routing-calls-raised.md`; the chunk that settles them cites their stamp there. The figures came from 276 chunks finished since the 2026-10-29 reset. Chunks started on Opus 5.5 at medium, 79 of them, took a mean 0.8 review rounds past each pass's first, 0.3 unfinished verdicts and 0.2 later fixes. Chunks started on Fable 5.2 at low, 5 of them, took 0.4, 0.0 and 0.0. On an Opus 5.5 project only L 4 items start on Fable 5.2 at low, so it did better on harder items. Two things weaken the evidence: 5 chunks is the fewest a call allows, and the Opus 5.5 figures include chunks from before Fable 5.2 joined the ladder. On the 2026-11-11 index, an L 3 task's cost rises about 1.3 times, from $2.45 to $3.10, for fewer rounds and fewer unfinished verdicts (goal 1.4). The chunks started on Sonnet 5.5 at high, 164 of the 276, don't move.
|
||||
|
||||
Valid while the index ranks these models, and while no newer model joins the catalog.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user