Is claude-haiku-4.5-max good at Knowledge & Docs?
claude-haiku-4.5-max ranks #58 of 94 for Knowledge & Docs — usable. The top pick for this task is gpt-5.4-max.
claude-haiku-4.5-max on each Knowledge & Docs sub-task
| Grounded Docs (No Fabrication) | 100.0/100 | #26 |
| Help-Center Article | 95.5/100 | #74 |
| Right Doc Type | 71.5/100 | #51 |
| Procedure / Runbook | 38.5/100 | #89 |
Real examples, graded
WeakSOP: handle a customer data-deletion request (Cedar & Sage) 28/100
“The model failed critical safety and structural requirements. The warning for the irreversible deletion was placed at the end of the document rather than before the destructive step. Additionally, the model grouped multiple actions into single steps using bullet points and fabricated a significant amount of company policy, timelines, and system features not provided in the prompt.”
Frequently asked
Is claude-haiku-4.5-max good at Knowledge & Docs?
claude-haiku-4.5-max ranks #58 of 94 models we tested for Knowledge & Docs, scoring usable.
What is claude-haiku-4.5-max's strongest Knowledge & Docs skill?
Its best sub-task here is Grounded Docs (No Fabrication).
This page is Spring Prompt, running
We just did this for every model. Do it for your prompt.
The rankings above come from running real tasks through real models and scoring every output. Spring Prompt is that same engine — pointed at your prompt, your test cases, and your definition of good.
- Generate test cases from your prompt — no eval set required to start.
- Compare models side by side with quality, cost and latency in one matrix.
- Optimise the winner until the scores say it's ready to ship.
Prompt × model results
12 test cases · 3 evals