ESG and carbon reporting · November 2026 Edition
Watershed vs Coolset
Zero of fourteen models named Watershed first on the direct prompt; zero named Coolset. Watershed was named by eleven of the fourteen models and Coolset by nine and Watershed carries 24 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 share6%2%Of first choices across the direct, paraphrase, budget and scale prompts, 0 to 100.
Negative rate17%0%Negative labels as a share of the product's labels, 0 to 100.
Rank in category#4#6A position in a field of 13; printed, not drawn.
Labels2415A count; the two differ.
The two percentage rows are drawn on one 0 to 100 track, Watershed 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 Watershed · Greenly vs Coolset · Persefoni vs Watershed
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.
WatershedFirst choices, of fourteen modelsCoolset
Direct00
Paraphrase213 against Watershed
Comparative10
Budget-constrained00
Scale-constrained101 against Watershed
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 Watershed 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 | | | |
Watershed Coolset first choice named as an alternative argued againstblank: not namedEach cell is one answer, Watershed on the left and Coolset on the right.The direct prompt
The plain question, one answer per model, grouped by where Watershed and Coolset stood in it.
Neither was the first choice, one was named
4 of 14 modelsThe answer put something else first and named one of the two as an alternative.Gemini 3.5 FlashGreenly alternatives: Gravity, KEY ESG, Novata, Sweep, Watershed
Perplexity SonarNovata alternatives: Coolset, Greenly, Novisto, Sweep
Qwen 3.7 FlashNovisto, Persefoni alternatives: ESG:ONE, Sweep, Watershed
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
Grok 4.20Sweep alternatives: Novisto, Persefoni
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
Coolset leads by two points.
Coolset2%#10 of 17Watershed0%#15 of 17Mid-marketThe figures above
The order flips: Watershed leads at mid-market.
Watershed6%#4 of 13Coolset2%#6 of 13Enterprise
Watershed leads by thirty-one points.
Watershed31%#2 of 11Coolset0%#– of 11What the models said about Watershed
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight 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
“Watershed, Workiva are powerful but priced for bigger organizations” DeepSeek V4 Flash · scale prompt · soft negative
“Most advanced AI and benchmarking (enterprise-grade but pricey)” Kimi K2 · paraphrase prompt · soft negative
“Mid-Market / Agile ESG & Carbon Platforms (Often the best fit for 500 employees): *Examples:* Watershed, Sweep, Position Green, Novata, Persefoni, Greenly.” Gemini 3.5 Flash · scale prompt · first choice
“Start by requesting demos from Watershed and Sweep. These two cover the vast majority of mid-sized B2B needs” Qwen 3.7 Flash · paraphrase prompt · first choice
“Best for: Enterprise climate and carbon accounting (Scope 1, 2, 3) with a focus on decarbonization action” DeepSeek V4 Flash · comparative 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.