Sweep vs Persefoni
Six of twelve models named Sweep first on the direct prompt; zero named Persefoni. Sweep was named by eleven of the twelve models and Persefoni by twelve and Sweep carries 37 labels and Persefoni 28, so the shares are not directly comparable.
Named in one category this edition.
Named in one category this edition.
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all twelve models, for a mid-market B2B company; rank is within the category; every quote names the model and the prompt it came from. Both figures come from the ESG and carbon reporting page.
By framing
SweepFirst choices, of twelve modelsPersefoni
Across every category in the September 2026 Edition, Sweep and Persefoni were named in the same answer thirty-six times, of the 73 answers naming Sweep and the 75 naming Persefoni. In those answers Persefoni took the first choice six times and Sweep five.
Every model, every framing
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | | |||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | | | | | | |
| Perplexity Sonar | | | | | ||
| Grok 4.1 Fast | | | | | | |
| Mistral Small | | | ||||
| DeepSeek V4 Flash | | | | | ||
| Llama 4 Maverick | | | ||||
| Qwen 3.7 Flash | | | | | ||
| Kimi K2 | | | | |||
| GLM 4.7 FlashX | | | | | ||
| MiniMax M2.5 | | | |
Sweep Persefoni first choice named as an alternative argued againstblank: not namedEach cell is one answer, Sweep on the left and Persefoni on the right.The direct prompt
Sweep first, Persefoni not the choice
6 of 12 modelsPersefoni was named in the answer but not as the choice, or not at all.Neither was the first choice, one was named
5 of 12 modelsThe answer put something else first and named one of the two as an alternative.Neither was named
1 of 12 modelsThe answer made no first choice from these two in this category.Bold names in an answer are the products the judge labeled a first choice; a model naming several gives each of them that label. The full answer text for every row is in the record.
By buyer segment
Sweep25%#1 of 15Persefoni6%#7 of 15What the models said about Sweep
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of five in this category shown.
“some unproven mid-market carbon tools like Sweep, Plan A... lack robust data governance” Grok 4.1 Fast · negative prompt · soft negative
“For most mid-market B2B companies, Sweep offers the strongest balance of supply chain support, framework coverage, and mid-market-appropriate pricing.” DeepSeek V4 Flash · direct prompt · first choice
“Sweep or Plan A are excellent choices... If you are in Europe and require CSRD alignment, Sweep is highly recommended.” Mistral Small · paraphrase prompt · first choice
“Sweep and EcoOnline appear to be the most consistently recommended options tailored to your size and needs” MiniMax M2.5 · direct prompt · first choice
What the models said about Persefoni
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of five in this category shown.
“Enterprise-grade platforms (like *Workiva*, *IBM Envizi*, or *Persefoni*) are usually overkill” Gemini 3.5 Flash · scale prompt · soft negative
“I'd choose Persefoni because it has a free single-user tier and is repeatedly positioned as the cheapest starting point” Perplexity Sonar · budget prompt · first choice
“### 1. Persefoni Pro (Free) ... Start with Persefoni's free tier” MiniMax M2.5 · budget prompt · first choice
“Top Recommendation: Persefoni ... robust free tier” Qwen 3.7 Flash · budget prompt · first choice
Comparisons are drawn for the top eight products in each category, each against each. The output is the models' output; nothing here is a recommendation by the index.