Benchmarks / DeckBench / Kestrel Logistics
Measured by Spring Prompt
Mistral Large 4: On-time delivery: what is going wrong and what to fund
For the board and the company's three main investors. The decision it supports: whether to fund 40 more drivers or a trunk re-plan with 10 drivers.
- Verdict
- Not presentable
- Deck rating
- 515
- Slides
- 6 (brief: 5-8)
- Design quality
- 17%
Why it is not presentable
- Layout defect: something off the slide, colliding, too small or too faint to read
- Showed a number the analysis does not support
- Made a material claim the analysis does not support
- A slide the judges rated as needing work
In detail
- Not supported by the analysis: slide 2: chart Network OTIF: 0.938.
- Not supported by the analysis: slide 2: chart Network OTIF: 0.932.
- Not supported by the analysis: slide 2: chart Network OTIF: 0.918.
- Not supported by the analysis: slide 2: chart Network OTIF: 0.925.
- Slide 2: “Network OTIF: W31 94.8%, W32 93.8%, W33 93.2%, W34 91.8%, W35 92.5%. These intermediate network figures are not supplied by the analysis and do not match simple averages of its depot figures.” is not supported by the analysis.
- Slide 2: “Network OTIF chart values W32 93.8%, W33 93.2%, W34 91.8%, W35 92.5%. The analysis gives only W29 and W36. The depot average gives about 94.5%, 94.0%, 92.4% and 93.2% for those weeks, so the chart puts the network below the 93% floor earlier and lower than the data shows.” is not supported by the analysis.
- Slide 5: “Insurer's estimate of damaged-goods claims: £280k. The analysis says this estimate is not agreed and must not be quoted.” is not supported by the analysis.
- Slide 2: “Network OTIF data for weeks 30 to 35 (95.5%, 94.8%, 93.8%, 93.2%, 91.8%, 92.5%)” is not supported by the analysis.