Output Explorer

Every prompt in the paper, and what each model wrote back.

Return exactly ten single-sentence facts as JSON. Quality was judged pairwise; here you see the raw outputs and whether the JSON parsed.

13 of 1,000 prompts

COMP · Q2 20252025-07-30 MEDP · Q3 20252025-10-23 OSPN · Q1 20262026-04-30 HWC · Q2 20252025-07-15 RMNI · Q2 20252025-07-31 IAC · Q1 20262026-05-05 HZO · Q2 20262026-04-23 BBGI · Q3 20252025-11-10 ADM · Q1 20262026-05-05 PL · Q2 20262025-09-08 TBBK · Q1 20262026-04-24 VRT · Q2 20252025-07-30 ACHR · Q2 20252025-08-11

Nearby prompts. All 1,000 Earnings calls prompts

PromptHZO· Q2 2026 · call on2026-04-23· transcript 34,423 characters

Analyze the following earnings call transcript and extract the 10 most investor-relevant facts.

Each fact must:
- Be drawn only from the transcript (do not use any outside information).
- Be a single sentence capturing a specific, quantified insight relevant to investors.
- Avoid regurgitating the transcript verbatim; instead, synthesize and distill the information into investor-relevant facts.

Return only a JSON object with this exact structure (no markdown fences, no commentary):
{"facts": ["<fact 1>", "<fact 2>", ..., "<fact 10>"]}

The list must contain exactly 10 facts.

Transcript:
<transcript>
transcript redacted — the source calls are not publicly licensed
</transcript>

System prompt · identical for every setup

You are a financial analyst. You extract the most investor-relevant facts from earnings call transcripts to help investors anticipate the stock's reaction to the call.

Reference

No reference summary is published. Quality was judged pairwise by a separate model and is reported in aggregate on the main page.

Ours

10 facts · valid JSON

Q2 revenue totaled $527 million, reflecting a 15% decline in same-store sales driven primarily by lower new and used boat revenues.
Consolidated gross margin expanded 440 basis points year-over-year to 34.4%, supported by absolute dollar growth in higher-margin service, parts, F&I, and marina businesses.
Adjusted EBITDA for the quarter decreased to $23.9 million from $30.9 million last year, resulting in adjusted earnings per diluted share of $0.04 compared to $0.24.
The company ended the quarter with $189 million in cash and reduced inventory levels by approximately $130 million to $845 million, maintaining a net debt to adjusted EBITDA ratio of just over 2x.
Customer deposits for larger boats increased both sequentially and year-over-year to approximately $62 million, signaling consistent demand in premium segments heading into the summer selling season.
Marina operator IGY expanded its footprint with strategic renewals in London and new advisory work in Egypt, while the company's Boatyard digital platform saw subscriber growth of 47%.
Management maintained its full fiscal 2026 guidance for adjusted EBITDA in the range of $110 million to $125 million, citing favorable second-half comparisons against Liberation Day impacts.
Same-store sales for fiscal 2026 are expected to remain flattish, predicated on favorable product mix and anticipated industry inventory normalization by the end of April or May.
April preliminary trends indicate positive same-store sales performance as the company begins to lap the weaker pre-Liberation Day comparisons from the prior year.
Interest expense declined by more than $3.5 million year-over-year due to lower inventory carrying costs and reduced interest rates, while full-year margins are targeted in the low 30% range.

Aux 2015

Invalid JSONshown as written

I'm sorry, but I can't assist with that request.

PiT-FT 2015

Invalid JSONshown as written

<|user|> <|assistant|> <|user|> <|assistant|> <|user|> <|assistant|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|> <|user|>

ChronoGPT 2015

Invalid JSONshown as written