ESG and carbon reporting · November 2026 Edition
Persefoni vs Coolset
One of fourteen models named Persefoni first on the direct prompt; zero named Coolset. Persefoni was named by thirteen of the fourteen models and Coolset by nine and Persefoni carries 30 labels and Coolset 15, so the shares are not directly comparable.
Named in one category this edition.
Named in one category this edition.
First-choice share17%2%Of first choices across the direct, paraphrase, budget and scale prompts, 0 to 100.
Negative rate10%0%Negative labels as a share of the product's labels, 0 to 100.
Rank in category#2#6A position in a field of 13; printed, not drawn.
Labels3015A count; the two differ.
The two percentage rows are drawn on one 0 to 100 track, Persefoni reading right to left. Rank and label count are printed, not drawn.Sweep was named alongside these two in nine of the fourteen direct answers. Greenly vs Persefoni · Greenly vs Coolset · Persefoni vs Sweep
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all fourteen 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
How many of the fourteen models made each the first choice, per way of asking, and how many argued against it.
PersefoniFirst choices, of fourteen modelsCoolset
Direct10
Paraphrase112 against Persefoni
Comparative00
Budget-constrained701 against Persefoni
Scale-constrained00
Negative00
Bars are first choices, 0 to 14 each sideModels that argued againstA model can name both, so the two sides of a row do not sum to fourteen.
Every model, every framing
The eighty-four answers behind the chart above, one cell each: where Persefoni and Coolset stood in it.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | | | ||||
| GPT-5.4 mini | | |||||
| Gemini 3.5 Flash | | |||||
| Perplexity Sonar | | | | | ||
| Grok 4.20 | | | | |||
| Mistral Small | | | ||||
| DeepSeek V4 Flash | | | ||||
| Llama 4 Maverick | | | ||||
| Qwen 3.7 Flash | | | | |||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | | | | |||
| MiniMax M2.5 | | | | |||
| GPT-6 Luna | | | | |||
| Muse Glimmer 30B | | | |
Persefoni Coolset first choice named as an alternative argued againstblank: not namedEach cell is one answer, Persefoni on the left and Coolset on the right.The direct prompt
The plain question, one answer per model, grouped by where Persefoni and Coolset stood in it.
Persefoni first, Coolset not the choice
1 of 14 modelsCoolset was named in the answer but not as the choice, or not at all.Qwen 3.7 FlashNovisto, Persefoni alternatives: ESG:ONE, Sweep, Watershed
Neither was the first choice, one was named
3 of 14 modelsThe answer put something else first and named one of the two as an alternative.Perplexity SonarNovata alternatives: Coolset, Greenly, Novisto, Sweep
Grok 4.20Sweep alternatives: Novisto, Persefoni
Muse Glimmer 30BEmerald Power alternatives: Coolset, ESG:ONE, Envoria, Normative, Sweep, cubemos
Neither was named
10 of 14 modelsThe answer made no first choice from these two in this category.Claude Haiku 4.5EcoOnline ESG alternatives: Diligent ESG, Novisto, Sweep
GPT-5.4 miniWorkiva ESG alternatives: FigBytes, Horizon ESG, KEY ESG, Metrio
Gemini 3.5 FlashGreenly alternatives: Gravity, KEY ESG, Novata, Sweep, Watershed
Mistral SmallEmerald Power, Horizon ESG alternatives: Metrio, Position Green
DeepSeek V4 FlashGreenly, cubemos alternatives: Emerald Power, Horizon ESG, Sweep
Llama 4 Maverickno first choice
Kimi K2ESG:ONE alternatives: Diligent ESG, EcoOnline ESG, Greenly
GLM 4.7 FlashXEmerald Power alternatives: Atlas Metrics, Greenly, Normative, Novato, Sweep
MiniMax M2.5Novisto, Precoro ESG alternatives: IBM Envizi, Workiva ESG
GPT-6 LunaSweep alternatives: Greenly, Workiva ESG
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
The same question asked on behalf of a different buyer. Each standing is computed within its segment and they are never added together. The figures above are the mid-market standing, which is the one the category orders by.
Small business
Persefoni leads by sixteen points.
Persefoni18%#2 of 17Coolset2%#10 of 17Mid-marketThe figures above
Persefoni leads by fifteen points.
Persefoni17%#2 of 13Coolset2%#6 of 13Enterprise
What the models said about Persefoni
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of seven in this category shown.
“technically rigorous but are generally framed for enterprises & financial institutions with complex regulatory needs and pricing/complexity” Muse Glimmer 30B · paraphrase prompt · soft negative
“The paid tier jumps to ~$55k/year, which is unrealistic for most small companies.” DeepSeek V4 Flash · budget prompt · soft negative
“far more accessible than enterprise platforms like Persefoni ($50K–$200K)” DeepSeek V4 Flash · paraphrase prompt · soft negative
“It is widely considered the most accessible platform for companies that don't have a large sustainability team.” Qwen 3.7 Flash · direct prompt · first choice
“Best budget pick: Persefoni Pro—if your main need is carbon accounting and climate reporting.” GPT-6 Luna · budget prompt · first choice
“The best ESG reporting software for a company with a limited budget is Persefoni, which is free.” Llama 4 Maverick · budget prompt · first choice
What the models said about Coolset
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Three of four in this category shown.
“the most recommended carbon accounting platforms are Greenly and Coolset” Mistral Small · paraphrase prompt · first choice
“Coolset - Best for mid-sized companies that need structure, speed, and clarity without enterprise-level complexity.” Llama 4 Maverick · paraphrase prompt · alternative
“Best for: Mid-market companies needing structure and speed without enterprise-level complexity” GLM 4.7 FlashX · paraphrase prompt · alternative
Also compared
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.