The mistakes that keep costing tasks

The deliverable misses its type's complexity floor.

A rule reads off records the assigned universe does not hold, such as a catalog or a policy page, while prompts, inputs and criteria read as if they were there.

In Leg B, a turn you send Model B hands it what it had to work out: a value, a count, a position or the conclusion.

A Leg A prompt that hands Model A a file also states what the file exists to make it read, such as a count or which document is current.

Something in the input folder, open to both models from turn 1, previews a later turn: a file named for its turn, or a document carrying a later instruction.

Modifier or Assets Delivered misdescribes the milestone's Leg A turn: deferred_asset or revision on Leg A turn 1, none as a modifier, a bare extension for a filename, or a deferred file no row lists.

Continuation criteria, read in Leg B to decide when Model B moves on, either miss one of their Leg A turn's asks or demand what that turn cannot produce, such as a later turn's file.

A Leg A turn no milestone covers, usually from a set stopping a turn short, or two milestones on one turn with identical intent and clauses.

Too few negatives for the scenario's traps, so taking the bait costs nothing extra, or a negative worded as the virtue, which marks down correct runs.

A prompt requirement no criterion checks, or a criterion no turn asked for, usually written from the golden.

Weights that ignore difficulty: a cross source derivation weighted like a direct read, or one operation at 5 in one row and 3 in the next.

More than five criteria target Trajectory.

The criteria Model A fails carry under half the rubric's weight, both blocks counted.

Your golden fails a criterion that is wrong about the task: a rule only the Desired Outcome states, a phrase at a different length than the golden renders, or a file the inputs archive lacks.

A criterion stricter than its source fails correct runs: it pins a figure the source leaves open, picks one answer of several, insists on one of two sources, or scopes to a step that lacks the values.

Category or Evaluation Target does not fit the criterion: Agent Behavior or Tool Use on an artifact, a category in the target field, or a subjective row tagged Instruction Following.

Two criteria decided by the same evidence: one inside a broader one, a negative mirroring a positive, or a subjective criterion restating an objective value.

Subjective criteria describe features without naming the file that carries them, usually after the first one or two.

The subjective block holds fewer than ten criteria, or more than 30% of the total weight.

A subjective criterion requires the exact heading or label your golden happens to use, words no prompt contains.

The golden states a value its source, or its own page, contradicts, often one true at an earlier turn.

A revision changes what was asked but leaves wording that depended on it, so the artifact states the old position and the new one.

Five cheap checks, often skipped: stray files in the golden archive, a filename spelled two ways, a golden that stops early, no starred run, and clauses a grader must decode.