Six of fourteen models named Thomson Reuters ONESOURCE Tax Provision first on the direct prompt; six named Bloomberg Tax Provision. Both were named by all fourteen models and Thomson Reuters ONESOURCE Tax Provision carries 57 labels and Bloomberg Tax Provision 52, 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 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 corporate tax provision page.
Across every category in the October 2026 Edition, Thomson Reuters ONESOURCE Tax Provision and Bloomberg Tax Provision were named in the same answer 102 times, of the 159 answers naming Thomson Reuters ONESOURCE Tax Provision and the 118 naming Bloomberg Tax Provision. In those answers Bloomberg Tax Provision took the first choice twenty-four times and Thomson Reuters ONESOURCE Tax Provision thirty.
| 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 | ||||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B |
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.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“explicitly says to avoid or be cautious about Longview, ONESOURCE, Workiva, Oracle Tax Reporting, and Corptax” Perplexity Sonar · negative prompt · hard negative
“"Avoid for now: OneSource, Corptax, Longview – these are enterprise-grade tools with enterprise-grade price tags."” Muse Glimmer 30B · negative prompt · hard negative
“Avoid Bloomberg Tax Provision, Thomson Reuters ONESOURCE, and other enterprise\u2011grade provision platforms” GLM 4.7 FlashX · budget prompt · hard negative
“Often tops lists for consolidated provisions... ONESOURCE in audit-proofing; Analyst reports like Gartner often rate ONESOURCE/Vertex highly for this segment.” Grok 4.1 Fast · direct prompt · first choice
“Thomson Reuters ONESOURCE Tax Provision is the most cited first choice in the mid-market set, and is the accepted enterprise standard” Muse Glimmer 30B · paraphrase prompt · first choice
“1. ONESOURCE Tax Provision (by Thomson Reuters) ... Real-time capabilities and robust integration with other tax workflow tools.” Mistral Small · comparative prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“"Avoid Bloomberg Tax Provision and Thomson Reuters ONESOURCE unless you have a large staff and a budget exceeding $25k–$50k/year."” Muse Glimmer 30B · negative prompt · hard negative
“Avoid Bloomberg Tax Provision, Thomson Reuters ONESOURCE, and other enterprise\u2011grade provision platforms” GLM 4.7 FlashX · budget prompt · hard negative
“Also targeted at large enterprises, this tool is not cost-effective for smaller operations.” Mistral Small · negative prompt · hard negative
“look for mid-market, native-cloud software (such as *Bloomberg Tax Provision* or *TaxProvision.net*) that emphasizes quick, out-of-the-box onboarding” Gemini 3.5 Flash · negative prompt · first choice
“Mid-Market Specialists (e.g., Bloomberg Tax Provision): Built specifically to replace Excel for mid-market tax teams.” Gemini 3.5 Flash · scale prompt · first choice
“Tools like Bloomberg and ONESOURCE often top mid-size lists for traceable workflows and integrations.” Grok 4.1 Fast · scale 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.