HoldsHolds on claude-haiku-4-5Holds on gpt-5-miniNo measured effect on gemini-3.1-flash-lite
Splitting big tasks
Prompt chaining: does splitting a task across prompts work?
Break a big task into a few prompts, one step at a time.
Why it matters
A task with several parts gives a model several chances to drop one. Doing the parts in turn keeps each one in view.
How to use it
Ask for the first step, then feed its answer into the next prompt. Best on tasks with several parts. Check that it helps on the model you use.
Pass rate up 10 to 25 points on all three models.
What the marks mean
- Holds
- No measured effect
Show the per-model numbers
Claim tested: Breaking a complex task into separate sequential prompts beats one combined prompt.
Holds on claude-haiku-4-5 and gpt-5-mini. No measured effect on gemini-3.1-flash-lite.
Circulates in practitioner communities. Tested because it circulates, not because it is endorsed.
This tip is OpenAddict's plain-language read of the measured result. The measurement below is the evidence, and it is what the reading has to answer to.
Ledger idC14-prompt-chaining
What was tested
This claim circulates in practitioner communities as advice about how to write prompts. That it circulates is an input to what gets tested here. It is a reason to test the claim, and it is not evidence for or against it. The result below is the evidence, and it is the only thing on this page that carries weight.
The comparison is paired. Two prompts differ in one respect, the manipulated variable, and are otherwise identical by construction. Nothing here supports a causal reading beyond that pairing.
Result
| Measure | claude-haiku-4-5 | gpt-5-mini | gemini-3.1-flash-lite |
|---|---|---|---|
| Control arm | 0.767n 10 | 0.753n 10 | 0.900n 10 |
| Treatment arm | 1.000n 10 | 1.000n 10 | 1.000n 10 |
| Delta | +0.233 | +0.247 | +0.100 |
| Interval, 95 percent | 0.134 to 0.333 | 0.162 to 0.332 | 0.000 to 0.200 |
| Orbit | Stable100 of 100 records | Stable100 of 100 records | In free drift100 of 100 records |
Orbit is assigned by the frozen status_v1 rule. On this scale, deterministic pass rate, 0 to 1, the pass threshold is +0.20 and the failure floor is -0.20, each requiring an interval that excludes zero.
Method for this claim
- Task set
- 10 three-part tasks of the extract-then-compute-then-report class. The control arm asks for all three parts in one prompt; the treatment arm asks for them in three turns, each seeing the previous answer verbatim. Scored only on the final output, against committed literal keys: the computed figures must appear and the stated shape must hold.
- Runs per model per arm
- 50
- Scoring
- Deterministic, via scoreRequirementKeys. A committed function scores each answer with no model in the loop.
- Pass criterion as written for the pilot
- Treatment mean requirement satisfaction exceeds control by at least 0.10 on the same 10 tasks.
The published verdict comes from status_v1, not from the pass criterion above. The criterion is recorded because it is what the claim was registered with before the run.
Model versions, as recorded
| Model | Version string returned | Delta on this claim | Interval |
|---|---|---|---|
| claude-haiku-4-5 | claude-haiku-4-5-20251001 | +0.233 | 0.134 to 0.333 |
| gpt-5-mini | gpt-5-mini-2025-08-07 | +0.247 | 0.162 to 0.332 |
| gemini-3.1-flash-lite | gemini-3.1-flash-lite | +0.100 | 0.000 to 0.200 |
Reading across models
Sampling was not held constant across vendors, so comparing one model column against another compares two settings as well as two models.
gpt-5-mini rejected the fixed sampling setting and ran at its own default on all 1040 of its calls. The other models ran at temperature 0.