Category · Consulting companies for AI transformation

Which consulting firm should a Fortune 500 company hire for an AI transformation?

14 AI models · 125 answers · ranked by score

ordered by brand score: 100 pts for rank 1 → 20 for rank 5 · no mention = 0

  1. #1McKinsey & Company
    87
    brand score
    75first choice
    12345
  2. #2Accenture
    78
    brand score
    64first choice
  3. #3Boston Consulting Group
    63
    brand score
    38first choice
  4. #4Deloitte
    44
    brand score
    28first choice
  5. #5Bain & Company
    12
    brand score
    9first choice
Show 3 more
  1. #6IBM Consulting
    10
    brand score
    9first choice
  2. #7PwC
    3
    brand score
    3first choice
  3. #8EY
    0
    brand score
    0first choice

Each bar covers the middle half of one model’s answers (Q1–Q3); the line inside it is that model’s median rank for the times it recommended the brand. The badge under a brand says how far apart the models are on it, and “first choice” scores rank 1 far above the rest — a brand can place well overall and still rarely lead an answer.

Swipe left for the full report

Category · Consulting companies for AI transformation

Brand by model

Median rank each model gave each brand.

Scroll the table sideways to see every model →

deepseek-v4.1-flashgpt-6-astragemini-3.8-flashgemini-3.7-flashgrok-4.6qwen3.8-maxclaude-opus-5gemini-3.5-flash-litekimi-k3gpt-5.6-lunagpt-5.6-solgpt-5.6-terramistral-medium-3.5claude-haiku-4.5
McKinsey & Company2.02.01.01.01.02.01.01.01.02.03.02.01.01.0
Accenture1.01.03.03.03.01.02.03.02.01.01.01.03.54.0
Boston Consulting Group3.53.02.02.02.03.03.02.03.03.54.04.02.02.0
Deloitte3.54.04.55.04.04.04.04.04.03.52.03.04.53.5
Bain & Company5.0—4.04.05.05.0—5.05.05.0—5.03.03.0
IBM Consulting5.05.05.05.05.05.05.0—5.05.05.05.0—5.0
PwC——5.0—5.0——5.0—5.0——5.05.0
EY—————————————5.0
1st
2
3
4
5th

A dash means that model never named the brand in any of its runs. Deeper blue is better: rank 1 is the brand a model would recommend first.

Category · Consulting companies for AI transformation

Where the models disagree

1 of 8 brands split the panel. Each mark is one model's score for the brand, on the same 0–100 scale as the ranking.

  1. #2Accenture

    claude-haiku-4.5 40 → gpt-6-astra 100

  2. #1McKinsey & Company

    gpt-5.6-sol 52 → mistral-medium-3.5 100

  3. #3Boston Consulting Group

    gpt-5.6-terra 40 → mistral-medium-3.5 80

  4. #4Deloitte

    gemini-3.7-flash 28 → gpt-5.6-sol 72

  5. #5Bain & Company

    claude-opus-5 0 → mistral-medium-3.5 30 · 3 of 14 never named it

  6. #6IBM Consulting

    gemini-3.5-flash-lite 0 → gpt-5.6-sol 28 · 2 of 14 never named it

A hollow mark is a model that never named the brand in any of its runs, which scores 0. Agreement is not endorsement — a brand every model ignores equally agrees just as tightly as one they all rank first.

Category · Consulting companies for AI transformation

Named, and named first

Across → how frequently the panel names the brand at all.
Up ↑ how often the answers that name it put it first.

the default answera narrow favouritelisted, rarely ledthe long tail12345678
  1. 1McKinsey & Company99/55
  2. 2Accenture99/45
  3. 3Boston Consulting Group99/0
  4. 4Deloitte99/0
  5. 5Bain & Company40/0
  6. 6IBM Consulting44/0
  7. 7PwC14/0
  8. 8EY1/0

The horizontal line sits at 20% — the rate a named brand would lead at if the models were picking one of its 5 slots at random. Above it they are choosing it first on purpose. Both figures average across models, so a thinly sampled model counts the same as a heavily sampled one.

Category · Consulting companies for AI transformation

What the models actually said

Models
14
Answers
125

McKinsey & Company leads with a score of 87 of 100, ranked by 14 of 14 models.

The panel agrees on the top tier—McKinsey and Accenture both appear in every model's ranking—but splits sharply on which firm should lead. Models divide into two camps: one places McKinsey first and Accenture second or third, the other reverses that order entirely. This is the study's central fault line.

McKinsey & CompanyAccenture
  • 100claude-haiku-4.540
  • 100mistral-medium-3.550
  • 100gemini-3.5-flash-lite56
  • 100gemini-3.7-flash60
  • 100gemini-3.8-flash64
  • 98grok-4.668
  • 96claude-opus-584
  • 92kimi-k388
  • 86deepseek-v4.1-flash90
  • 72qwen3.8-max88
  • 78gpt-5.6-luna100
  • 78gpt-6-astra100
  • 72gpt-5.6-terra100
  • 52gpt-5.6-sol100

McKinsey & Company ahead on 8 of 14 models

McKinsey scores 87.43 overall and earns first place from eight models, anchored by unanimous support from the Gemini family, Claude Haiku, Mistral, Grok, and Kimi. Accenture posts 77.71 but claims first from all four GPT models (Luna, Sol, Terra, Astra) plus DeepSeek and Qwen. The split appears to track how each model weighs strategic prestige against delivery scale. Models favoring McKinsey emphasize board-level credibility, transformation roadmaps, and thought leadership; those choosing Accenture cite end-to-end execution muscle, multi-billion-dollar AI investments, tens of thousands of practitioners, and the ability to move from strategy through systems integration to managed services at global volume. Both camps acknowledge the other firm's strengths—no model dismisses either—but the choice of which capability matters more produces a 60-point swing in Accenture's per-model scores (40 to 100) and a 48-point span for McKinsey (52 to 100).

gpt-6-astra
100
rates it highest
claude-haiku-4.5
40
rates it lowest

Accenture · 60 points apart on a 0–100 scale

Sources align with the narratives each camp builds. McKinsey partisans cite McKinsey State of AI reportwww.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai×8, Harvard Business Review×21, and Forbeswww.forbes.com×53—research that shapes how executives frame AI in the first place. Accenture supporters lean on Gartnerwww.gartner.com×68, Forrester×31, and IDC MarketScape×29—analyst reports that assess implementation track record, partnership ecosystems, and delivery capacity. The hypothesis is that models trained or fine-tuned with heavier representation of business press and thought leadership tilt toward McKinsey, while those exposed to more vendor-evaluation content favor Accenture. The data does not confirm this directly, but the source clusters are consistent with it.

Boston Consulting Group sits in a zone of broad agreement (scores 40–80, median rank 2–4) that every model populated, yet none named it first. The reasoning converges: BCG X gives the firm credible build capability alongside strategy, and models repeatedly cite the 10-20-70 framework (ten percent algorithms, twenty percent technology, seventy percent people and process) as evidence of grounded insight. But execution scale trails Accenture and strategic AI brand sits narrowly behind McKinsey. BCG Xwww.bcg.com/x×35 dominates the recalled sources (35 mentions), suggesting models anchor on that unit as BCG's differentiator yet still see it as smaller than the top two.

Deloitte earns universal coverage (brand score 44.43, every model ranked it) with a tight span (28–72) and consistent positioning in ranks 2–5. The agreement is thematic rather than ordinal: models uniformly frame Deloitte as the choice when AI must integrate with governance, risk, audit, regulatory, and legacy enterprise systems—especially in heavily regulated industries—but less compelling for cutting-edge strategy or frontier innovation. Deloitte AI Institute×31 appears 31 times, more than any other firm-specific source, indicating models recall the research yet interpret it as evidence of governance depth rather than strategic differentiation. One model (GPT-5.6-sol) scores Deloitte at 72 and ranks it second, an outlier that may reflect heavier weighting of compliance and enterprise breadth in that variant's training or prompt handling.

Bain registers as credible but secondary (brand score 12.29, ranked by 11 models, most often fifth). Every mention acknowledges the OpenAI partnership as a meaningful asset—access to frontier generative models and early use cases—but no model elevated Bain above mid-pack, citing smaller global delivery footprint and limited systems-integration capacity. The partnership appears in reasoning but does not override scale concerns, suggesting models treat alliances as enhancing rather than substituting for in-house capability.

IBM Consulting and the remaining Big Four (PwC, EY) occupy the tail. IBM scores 9.57 and appears on twelve lists, always at fifth when ranked; every model flags platform bias risk (watsonx, Red Hat) and positions IBM as stronger on engineering and infrastructure than board-level strategy. PwC (2.71, six models) and EY (0.29, one model) are seen as audit-heritage firms with AI capabilities but not AI identities. The convergence here is striking: models agree these firms are credible in narrow contexts—compliance, controls, IBM-heavy environments—but not default choices for transformation. IBM watsonxwww.ibm.com/watsonx×10 appears ten times, yet models interpret it as evidence of product depth rather than consulting independence, reinforcing the neutrality concern.

The panel agrees on who belongs in the conversation but splits on whether Fortune 500 AI transformation demands McKinsey's strategic influence or Accenture's execution scale—a divide that appears to reflect each model's prior exposure to thought leadership versus implementation case studies.

The recalled-source distribution offers a plausible mechanism. Gartner (116 mentions across variants), Forrester (31), and IDC (46) dominate—all assess delivery and vendor ecosystems—yet Harvard Business Review (50) and Forbes (53) also rank high, and these skew toward executive perspective and strategic framing. Models citing more HBR and Forbes in their McKinsey reasoning tend to rank McKinsey first; those leaning on Gartner and IDC for Accenture rank Accenture first. This is a hypothesis, not proof, but the source clusters and ranking patterns move together. The study captures a field where the top consultancies occupy different reputational niches—strategy convening versus scaled execution—and language models, drawing on diverse training corpora, weight those niches differently.

Category · Consulting companies for AI transformation

What shaped the answers

364 sources across 1683 references, grouped by site from 698 recalled names. The top 5 carry 35% of them.

Sources are what each model recalled as having shaped its view. It does not mean that the sources were actually used in training. Recalled URLs might also be invalid or hallucinated.

BCG X×146 · 9%

bcg.com

Category · Consulting companies for AI transformation
#1

McKinsey & Company

also named McKinsey, McKinsey & Company (QuantumBlack)

87
brand score
75first choice
12345

Summary

McKinsey & Company earns exceptional consensus across the panel, achieving a brand score of 87.43 and appearing in every model's ranking. The firm receives broad agreement in its scoring, though the range spans 52 to 100, reflecting a split between models that rank it consistently first and those that place it second or third while still acknowledging its strategic strength. The central theme is McKinsey's combination of C-suite credibility with technical delivery through QuantumBlack: models repeatedly emphasize its ability to connect board-level AI strategy, operating-model redesign, and value prioritization with genuine data science and engineering capability. Sources such as McKinsey State of AI reportwww.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai×8, Harvard Business Review×21, and Forbeswww.forbes.com×53 underpin observations that McKinsey's research shapes how Fortune 500 executives frame AI transformation, giving it unusual influence at the agenda-setting stage.

McKinsey & Company

per-model scores 52–100 of 100 · mean 87 across 14 models

A secondary theme qualifies that strength: many models note that while McKinsey excels at defining the transformation roadmap and securing executive alignment, companies pursuing heavy systems integration or long-term managed operations may need to pair it with additional implementation partners. Analyst and industry sources including Gartner×48 and Forrester Wave: AI Consultancies×10 support the view that the firm's premium positioning and strategy-first culture can mean lighter hands-on delivery at scale compared to pure systems integrators, even as QuantumBlack adds meaningful technical depth.

“McKinsey combines top-tier C-suite strategy access with QuantumBlack, its dedicated AI/data science arm that delivers actual model and platform builds rather than slideware.”

— claude-opus-5

“McKinsey has the deepest bench of AI expertise combined with proven experience transforming Fortune 500 operations across industries.”

— claude-haiku-4.5

Per model summary

  • claude-haiku-4.5
    brand score
    100
    first choice
    100
    median rank
    1.0
    present in
    10/10

    This model consistently emphasizes McKinsey's deep bench of AI expertise, proven track record with Fortune 500 companies at scale, and proprietary research on AI adoption that provides industry-leading methodologies for comprehensive transformations.

  • claude-opus-5
    brand score
    96
    first choice
    90
    median rank
    1.0
    present in
    10/10

    This model always highlights the combination of QuantumBlack's engineering capability with C-suite strategy access, and repeatedly points to McKinsey's influential research shaping how boards frame AI value, while noting premium cost and lighter implementation at scale.

  • gemini-3.5-flash-lite
    brand score
    100
    first choice
    100
    median rank
    1.0
    present in
    10/10

    This model uniformly describes McKinsey as the industry leader combining deep C-suite advisory with QuantumBlack's technical execution, emphasizing proprietary frameworks, global footprint, and consistent ability to deliver measurable value at enterprise scale.

  • gemini-3.7-flash
    brand score
    100
    first choice
    100
    median rank
    1.0
    present in
    5/5

    This model repeatedly emphasizes McKinsey's seamless pairing of world-class C-suite strategic transformation with deep technical execution through QuantumBlack, highlighting their proven track record in enterprise-scale change management and measurable business value.

  • gemini-3.8-flash
    brand score
    100
    first choice
    100
    median rank
    1.0
    present in
    10/10

    This model consistently highlights McKinsey's combination of top-tier C-suite strategic advisory with QuantumBlack's technical implementation capabilities, emphasizing their ability to bridge high-level business strategy with operational AI deployment and measurable balance-sheet value.

  • grok-4.6
    brand score
    98
    first choice
    95
    median rank
    1.0
    present in
    10/10

    This model consistently emphasizes McKinsey's QuantumBlack unit, C-suite relationships, and thought leadership research as enabling high-impact AI transformations that tie technology directly to enterprise value at Fortune 500 scale.

  • kimi-k3
    brand score
    92
    first choice
    80
    median rank
    1.0
    present in
    10/10

    This model repeatedly highlights McKinsey's combination of unmatched C-suite credibility with QuantumBlack's technical depth, noting that its influential research shapes board-level AI agendas, though large-scale implementation may require additional delivery partners.

  • mistral-medium-3.5
    brand score
    100
    first choice
    100
    median rank
    1.0
    present in
    10/10

    This model uses nearly identical language across all reasonings, consistently describing McKinsey as a global leader with deep expertise in enterprise-scale AI adoption and highlighting QuantumBlack and proprietary tools as making them a top choice.

  • deepseek-v4.1-flash
    brand score
    86
    first choice
    65
    median rank
    2.0
    present in
    10/10

    This model consistently positions McKinsey as strongest for board-level strategy, operating-model redesign, and setting transformation direction through QuantumBlack, while noting it may need implementation partners for full-scale technology build.

  • gpt-5.6-luna
    brand score
    78
    first choice
    48
    median rank
    2.0
    present in
    10/10

    This model consistently positions McKinsey as strong for CEO-level strategy, operating-model redesign, and use-case prioritization, but notes clients may need additional partners for large-scale technology implementation and ongoing operations.

  • gpt-5.6-terra
    brand score
    72
    first choice
    43
    median rank
    2.0
    present in
    5/5

    This model consistently describes McKinsey as compelling for CEO-level strategy, operating-model redesign, and executive alignment around value creation, while advising clients to validate hands-on engineering capacity for implementation-heavy programs.

  • gpt-6-astra
    brand score
    78
    first choice
    48
    median rank
    2.0
    present in
    10/10

    This model uniformly positions McKinsey as strongest when the challenge is deciding where AI creates value and securing executive alignment for organizational change, but places it below Accenture for extensive systems integration and ongoing operations.

  • qwen3.8-max
    brand score
    72
    first choice
    48
    median rank
    2.0
    present in
    9/10

    This model consistently positions McKinsey as strongest for board-level strategy, value prioritization, and CEO-level alignment through QuantumBlack, while noting it may be less ideal as sole delivery partner for heavy engineering and systems integration.

  • gpt-5.6-sol
    brand score
    52
    first choice
    32
    median rank
    3.0
    present in
    5/5

    This model repeatedly emphasizes McKinsey's strength in connecting AI to corporate strategy, organizational redesign, and business value creation through QuantumBlack, while noting that extensive implementation may require additional integration partners.

Sources per model

Each model’s own references for this brand, grouped by site. Tile area is that site’s share of the model’s references; tap one for the pages behind it.

deepseek-v4.1-flash17 sites · 30 references
McKinsey QuantumBlack×9 · 30%

mckinsey.com

gpt-6-astra5 sites · 20 references
gemini-3.8-flash7 sites · 30 references
Forbes×10 · 33%

forbes.com

  • ×10/
gemini-3.7-flash5 sites · 15 references
Forbes×5 · 33%

forbes.com

grok-4.69 sites · 28 references
McKinsey×10 · 36%

mckinsey.com

qwen3.8-max11 sites · 27 references
McKinsey & Company×10 · 37%

mckinsey.com

claude-opus-513 sites · 30 references
McKinsey State of AI report×18 · 60%

mckinsey.com

gemini-3.5-flash-lite3 sites · 21 references
Forbes×10 · 48%

forbes.com

  • ×10/
kimi-k312 sites · 30 references
McKinsey & Company×15 · 50%

mckinsey.com

gpt-5.6-luna5 sites · 27 references
gpt-5.6-sol6 sites · 15 references
gpt-5.6-terra2 sites · 12 references
McKinsey — The State of AI×11 · 92%

mckinsey.com

mistral-medium-3.53 sites · 30 references
Forbes×10 · 33%

forbes.com

  • ×10/
claude-haiku-4.517 sites · 30 references
Harvard Business Review×7 · 23%

no URL recalled

  • ×7named without a URL

Sources are what each model recalled as having shaped its view. It does not mean that the sources were actually used in training. Recalled URLs might also be invalid or hallucinated.

Category · Consulting companies for AI transformation
#2

Accenture

78
brand score
64first choice
12345

Summary

Accenture commands very strong support across the panel, posting a brand score of 77.71 and appearing in every model's ranking. Yet that consensus masks a striking division in how the models position the firm: some place it as the unambiguous first choice for Fortune 500 AI transformation, while others slot it third or fourth, praising execution muscle but questioning strategic depth. The span of per-model scores runs from 40 to 100, and the report labels the disagreement "models split."

Accenture

per-model scores 40–100 of 100 · mean 78 across 14 models

The core theme is scale and delivery capacity. Models consistently cite Accenture's multi-billion-dollar AI investment, tens of thousands of practitioners, deep partnerships with Microsoft, NVIDIA, AWS and Google, and the ability to move from strategy through data engineering, systems integration, change management and managed services at global volume. Analyst reports from Gartner×48, Forrester×31 and IDC×17 anchor these claims, alongside Accenture's own disclosures of generative AI bookings and workforce commitments. Models that rank it first emphasize end-to-end execution as the decisive capability for enterprise transformation; those that rank it third or fourth acknowledge the same delivery strength but frame it as tilted toward implementation rather than boardroom strategy, yielding ground to pure strategy houses on high-level vision. A secondary theme is industry reach and technology neutrality: the firm's broad cloud alliances and sector-specific accelerators are seen as reducing platform lock-in and speeding production deployment, though concerns about cost, complexity and variable team quality appear in the caveats.

“Accenture is consistently recommended as the default first choice for Fortune 500 end-to-end AI transformation because it combines strategy with data engineering, systems integration, workforce change, and ongoing operations at global scale.”

— gpt-6-astra

“Accenture is characterized by unmatched global scale and systems integration capabilities backed by multi-billion-dollar AI investments, excelling at operationalization and technical deployment while being somewhat less focused on pure strategic advisory.”

— gemini-3.8-flash

Per model summary

  • deepseek-v4.1-flash
    brand score
    90
    first choice
    82
    median rank
    1.0
    present in
    10/10

    Accenture combines large-scale AI strategy with engineering and managed services delivery, making it well suited for Fortune 500 end-to-end transformation from pilots to enterprise-wide deployment through its global model and broad alliances.

  • gpt-5.6-luna
    brand score
    100
    first choice
    100
    median rank
    1.0
    present in
    10/10

    Accenture is consistently recommended as the strongest overall choice because it combines strategy with large-scale technology implementation, industry expertise, and managed services to move AI from pilots into enterprise-wide operating results.

  • gpt-5.6-sol
    brand score
    100
    first choice
    100
    median rank
    1.0
    present in
    5/5

    Accenture is positioned as the strongest default choice for Fortune 500 transformation because it combines AI strategy with large-scale systems integration, cloud partnerships, and global delivery capacity for enterprise-wide implementation.

  • gpt-5.6-terra
    brand score
    100
    first choice
    100
    median rank
    1.0
    present in
    5/5

    Accenture is described as the strongest all-around choice because it combines board-level strategy with large-scale technology delivery, managed services, and industry-specific implementation capacity to move from pilots to enterprise-wide transformation.

  • gpt-6-astra
    brand score
    100
    first choice
    100
    median rank
    1.0
    present in
    10/10

    Accenture is consistently recommended as the default first choice for Fortune 500 end-to-end AI transformation because it combines strategy with data engineering, systems integration, workforce change, and ongoing operations at global scale.

  • qwen3.8-max
    brand score
    88
    first choice
    85
    median rank
    1.0
    present in
    9/10

    Accenture is consistently positioned as the top choice because it combines AI strategy with large-scale implementation capabilities, industry expertise, and ecosystem partnerships to move Fortune 500 companies from pilots to enterprise-wide operational transformation.

  • claude-opus-5
    brand score
    84
    first choice
    60
    median rank
    2.0
    present in
    10/10

    Accenture is emphasized as the largest-scale AI implementation partner with unmatched delivery capacity, deep technology partnerships, and the ability to handle end-to-end enterprise deployment, though strategy depth may be somewhat thinner than pure strategy firms.

  • kimi-k3
    brand score
    88
    first choice
    70
    median rank
    2.0
    present in
    10/10

    Accenture is presented as having the industry's largest AI delivery capacity and implementation bench with multi-billion-dollar investments and deep technology alliances, making it the strongest choice for execution at Fortune 500 scale despite slightly less strategy prestige than top strategy firms.

  • gemini-3.5-flash-lite
    brand score
    56
    first choice
    32
    median rank
    3.0
    present in
    10/10

    Accenture is portrayed as a powerhouse in large-scale technical implementation and infrastructure deployment with unmatched execution capabilities, though their strength skews more toward systems integration than high-level strategic vision.

  • gemini-3.7-flash
    brand score
    60
    first choice
    33
    median rank
    3.0
    present in
    5/5

    Accenture offers unmatched global scale and systems integration capability with massive investments in AI, excelling at operationalizing technology across complex enterprise architectures, though they are more execution-focused than pure strategic firms.

  • gemini-3.8-flash
    brand score
    64
    first choice
    37
    median rank
    3.0
    present in
    10/10

    Accenture is characterized by unmatched global scale and systems integration capabilities backed by multi-billion-dollar AI investments, excelling at operationalization and technical deployment while being somewhat less focused on pure strategic advisory.

  • grok-4.6
    brand score
    68
    first choice
    43
    median rank
    3.0
    present in
    10/10

    Accenture is characterized by unmatched scale for executing large-scale AI transformations with deep technology partnerships and delivery capacity, though they are viewed as stronger in implementation and industrialization than in high-level strategic framing.

  • mistral-medium-3.5
    brand score
    50
    first choice
    29
    median rank
    3.5
    present in
    10/10

    Accenture combines strong AI consulting with robust implementation and technology capabilities, but is characterized as more execution-oriented than strategically focused compared to top-tier pure strategy firms.

  • claude-haiku-4.5
    brand score
    40
    first choice
    26
    median rank
    4.0
    present in
    10/10

    Accenture is consistently described as strong on execution and implementation but less focused on strategic advisory, positioning them as better suited for technology delivery than high-level transformation design.

Sources per model

Each model’s own references for this brand, grouped by site. Tile area is that site’s share of the model’s references; tap one for the pages behind it.

deepseek-v4.1-flash15 sites · 30 references
Accenture AI×7 · 23%

accenture.com

gpt-6-astra6 sites · 20 references
Accenture — Annual Reports×10 · 50%

accenture.com

gemini-3.8-flash9 sites · 30 references
Gartner×8 · 27%

gartner.com

gemini-3.7-flash7 sites · 15 references
Gartner×4 · 27%

gartner.com

grok-4.69 sites · 28 references
Accenture×10 · 36%

accenture.com

qwen3.8-max12 sites · 27 references
Accenture×7 · 26%

accenture.com

claude-opus-512 sites · 30 references
Accenture quarterly earnings releases on gen-AI bookings×8 · 27%

newsroom.accenture.com

gemini-3.5-flash-lite5 sites · 20 references
kimi-k315 sites · 30 references
Accenture×7 · 23%

accenture.com

gpt-5.6-luna6 sites · 27 references
Accenture Technology Vision×15 · 56%

accenture.com

gpt-5.6-sol8 sites · 15 references
Accenture Annual Report×8 · 53%

accenture.com

gpt-5.6-terra5 sites · 12 references
Accenture — AI services×7 · 58%

accenture.com

mistral-medium-3.55 sites · 30 references
Accenture AI×10 · 33%

accenture.com

claude-haiku-4.529 sites · 30 references
Accenture AI services overview×2 · 7%

no URL recalled

  • ×2named without a URL

Sources are what each model recalled as having shaped its view. It does not mean that the sources were actually used in training. Recalled URLs might also be invalid or hallucinated.

Category · Consulting companies for AI transformation
#3

Boston Consulting Group

also named BCG, Boston Consulting Group (BCG), Boston Consulting Group (BCG X)

63
brand score
38first choice
12345

Summary

Boston Consulting Group earns broad agreement across all fourteen models, with per-model brand scores spanning 40 to 80 and a combined average of 63.43. Every model ranked the firm, placing it consistently in the second-to-fourth positions—most often at rank two or three—but none named it first. This consistent mid-pack positioning reflects a shared view: BCG combines elite strategy with genuine technology-building capability through BCG X, making it compelling for innovation-led transformations, yet it trails Accenture in large-scale systems integration and delivery footprint and sits narrowly behind McKinsey in pure strategic prestige for AI-specific mandates.

Boston Consulting Group

per-model scores 40–80 of 100 · mean 63 across 14 models

The recurring theme across model reasoning is that BCG X gives the firm credible "strategy-plus-build" capability, bridging boardroom transformation agendas with hands-on product development, data science, and digital ventures. Models cite the firm's research on AI value realization—particularly the widely referenced 10-20-70 framework (ten percent algorithms, twenty percent technology, seventy percent people and process)—as evidence of practical insight into why most Fortune 500 AI programs fail. Sources underpinning this view include BCG Xwww.bcg.com/x×35, Harvard Business Reviewhbr.org×29, and MIT Sloan Management Reviewsloanreview.mit.edu×7. Models consistently note that BCG excels at identifying high-value use cases, business-model innovation, change management, and responsible AI governance, but acknowledge that its delivery scale for multi-year, enterprise-wide platform builds remains smaller than that of the leading systems integrators.

“BCG X gives BCG genuine build capability alongside strategy, and roughly a fifth of its revenue now comes from AI work, with well-regarded research on the '10-20-70' people-and-process split of AI value.”

— claude-opus-5

“BCG combines top-tier strategy talent with BCG X's tech-build capabilities and highly regarded research on AI value realization, though its global delivery scale for multi-year enterprise programs trails Accenture and its AI brand is marginally less established than McKinsey's.”

— kimi-k3

Per model summary

  • claude-haiku-4.5
    brand score
    80
    first choice
    50
    median rank
    2.0
    present in
    10/10

    BCG consistently offers strong AI transformation capabilities and practical implementation expertise, though it is positioned slightly behind McKinsey in specialized AI depth and market perception for pure AI strategy leadership.

  • gemini-3.5-flash-lite
    brand score
    80
    first choice
    50
    median rank
    2.0
    present in
    10/10

    BCG excels at AI transformation through BCG X by blending human-centric design with technical execution, focusing heavily on change management, workforce adoption, and responsible AI practices to ensure sustainable enterprise-wide deployment.

  • gemini-3.7-flash
    brand score
    80
    first choice
    50
    median rank
    2.0
    present in
    5/5

    BCG X enables the firm to combine elite business strategy with robust technical build capabilities, focusing on proprietary AI solutions and business model innovation that drive competitive differentiation and measurable ROI for large enterprises.

  • gemini-3.8-flash
    brand score
    76
    first choice
    47
    median rank
    2.0
    present in
    10/10

    BCG X integrates proprietary AI development and deep technical capabilities with strategic consulting, emphasizing custom solutions, organizational change management, and building lasting client capabilities rather than creating external dependency.

  • grok-4.6
    brand score
    74
    first choice
    45
    median rank
    2.0
    present in
    10/10

    BCG, via BCG X, combines elite strategy with hands-on AI build capabilities and innovative, collaborative approaches to transformation, though it trails slightly in delivery scale compared to Accenture and in pure strategic prestige compared to McKinsey.

  • mistral-medium-3.5
    brand score
    80
    first choice
    50
    median rank
    2.0
    present in
    10/10

    BCG excels in AI-driven business transformation through its Gamma platform and strong analytical capabilities, with particular focus on integrating AI into operations and delivering measurable, scalable outcomes for large-scale initiatives.

  • claude-opus-5
    brand score
    52
    first choice
    30
    median rank
    3.0
    present in
    10/10

    BCG X provides genuine build capability alongside strategy, with the firm emphasizing that most AI transformation value comes from people, process, and operating-model redesign (the 10-20-70 framework) rather than technology alone, though it has less large-scale systems integration capacity than Accenture.

  • gpt-6-astra
    brand score
    62
    first choice
    35
    median rank
    3.0
    present in
    10/10

    BCG combines enterprise strategy with BCG X's product-building capabilities for AI-enabled business reinvention, positioning it as a strong choice for innovation-led mandates though it sits narrowly behind for general transformations emphasizing both executive alignment and large-scale operational rollout.

  • kimi-k3
    brand score
    60
    first choice
    33
    median rank
    3.0
    present in
    10/10

    BCG combines top-tier strategy talent with BCG X's tech-build capabilities and highly regarded research on AI value realization, though its global delivery scale for multi-year enterprise programs trails Accenture and its AI brand is marginally less established than McKinsey's.

  • qwen3.8-max
    brand score
    52
    first choice
    29
    median rank
    3.0
    present in
    9/10

    BCG offers strong AI strategy and value-creation frameworks through BCG X that effectively link AI initiatives to business outcomes, though its end-to-end implementation footprint is viewed as slightly less broad than Accenture's for very large, multi-year Fortune 500 transformations.

  • deepseek-v4.1-flash
    brand score
    54
    first choice
    33
    median rank
    3.5
    present in
    10/10

    BCG X gives the firm strong AI venture-building and strategic capabilities for reimagining business models and high-value use cases, but it typically requires partners for very large-scale enterprise systems integration and deployment.

  • gpt-5.6-luna
    brand score
    50
    first choice
    29
    median rank
    3.5
    present in
    10/10

    BCG excels at business-led innovation, competitive strategy, and identifying where AI creates differentiated advantage, though it may require supplementing with larger implementation or managed-service partners for extensive Fortune 500 technology modernization.

  • gpt-5.6-sol
    brand score
    48
    first choice
    28
    median rank
    4.0
    present in
    5/5

    BCG combines strong executive-level strategy and product innovation with AI build capabilities through BCG X, making it attractive for differentiated transformations, though its global implementation and managed-services footprint is generally less extensive than leading systems integrators.

  • gpt-5.6-terra
    brand score
    40
    first choice
    25
    median rank
    4.0
    present in
    5/5

    BCG is compelling for value-led AI strategy, portfolio prioritization, and business-model innovation through BCG X, though it ranks below top-tier firms primarily when Fortune 500 transformations require extensive global systems-integration and managed-delivery footprints.

Sources per model

Each model’s own references for this brand, grouped by site. Tile area is that site’s share of the model’s references; tap one for the pages behind it.

deepseek-v4.1-flash17 sites · 30 references
BCG X×9 · 30%

bcg.com

gpt-6-astra5 sites · 20 references
BCG X×15 · 75%

bcg.com

gemini-3.8-flash12 sites · 30 references
IDC MarketScape×7 · 23%

idc.com

  • ×4named without a URL
  • ×3/
gemini-3.7-flash10 sites · 15 references
Gartner×3 · 20%

gartner.com

grok-4.612 sites · 24 references
BCG×10 · 42%

bcg.com

qwen3.8-max12 sites · 27 references
Boston Consulting Group×9 · 33%

bcg.com

claude-opus-513 sites · 30 references
BCG X×18 · 60%

bcg.com

gemini-3.5-flash-lite5 sites · 21 references
BCG X×10 · 48%

bcg.com

kimi-k313 sites · 29 references
Boston Consulting Group×13 · 45%

bcg.com

gpt-5.6-luna4 sites · 27 references
BCG Artificial Intelligence×20 · 74%

bcg.com

gpt-5.6-sol7 sites · 15 references
BCG Artificial Intelligence×8 · 53%

bcg.com

gpt-5.6-terra1 site · 12 references
BCG — Artificial Intelligence×12 · 100%

bcg.com

mistral-medium-3.55 sites · 30 references
claude-haiku-4.528 sites · 30 references
BCG AI and Analytics practice×2 · 7%

bcg.com

Sources are what each model recalled as having shaped its view. It does not mean that the sources were actually used in training. Recalled URLs might also be invalid or hallucinated.

Category · Consulting companies for AI transformation
#4

Deloitte

44
brand score
28first choice
12345

Summary

Deloitte earns a brand score of 44.43 and a first choice score of 28.1, placing it consistently in the middle of the pack across all fourteen models. Every model ranked the firm, and per-model scores span 28–72, which the study labels "broad agreement" despite a standard deviation of 12.59. The consensus positions Deloitte as a pragmatic, full-service option particularly valuable when AI transformation must integrate tightly with governance, risk, regulatory compliance, and complex enterprise systems—capabilities that matter most in heavily regulated Fortune 500 environments. Models repeatedly note that its breadth is both a strength and a constraint: the firm can mobilize multidisciplinary teams spanning strategy, implementation, cybersecurity, finance, tax, and audit-adjacent controls, yet that same scope can dilute focus, and delivery quality is flagged as variable by geography, practice, and engagement team. The firm's AI Institute, Trustworthy AI framework, and State of Generative AI in the Enterprise research series are cited as credible assets, but models consistently observe that Deloitte's brand skews toward risk, compliance, and enterprise integration rather than cutting-edge strategic differentiation or frontier AI innovation, leaving it trailing the top-tier strategy houses and Accenture on pure AI prestige.

Deloitte is recommended when AI governance, regulatory readiness, and enterprise-wide controls matter as much as the transformation itself—especially in regulated industries—though its strategic AI brand is perceived as less distinctive than specialized competitors.

Themes behind the rankings cluster around governance and compliance leadership, supported by repeated references to Deloitte AI Institute×31, Deloitte State of Generative AI in the Enterprise×3, the Trustworthy AI framework, and Gartner×48 assessments; enterprise breadth and integration muscle, valued for connecting AI to ERP, finance, risk, workforce, and legacy systems across complex organizations; and variable execution and generalist positioning, with models noting that scale and federated structure can produce inconsistent quality and that the firm is often seen as a dependable, lower-risk choice rather than a transformative or product-led innovator. The perception is pragmatic rather than aspirational: Deloitte is the firm to hire when regulatory scrutiny, auditability, and cross-functional orchestration dominate the agenda, but less so when frontier strategy or best-in-class AI engineering talent is the priority.

“Deloitte's breadth is unmatched—covering strategy, engineering, risk, regulatory, and audit-adjacent AI governance—making it especially strong for regulated Fortune 500 industries, though quality can vary significantly across its large global network.”

— claude-opus-5

“Deloitte is particularly attractive when AI must be integrated with enterprise processes, risk, regulatory compliance, finance, and workforce transformation across complex organizations, though delivery quality and strategic creativity can vary by team and geography.”

— gpt-5.6-sol

Per model summary

  • gpt-5.6-sol
    brand score
    72
    first choice
    45
    median rank
    2.0
    present in
    5/5

    Deloitte is particularly compelling when AI must be integrated with enterprise processes, risk, regulatory compliance, finance, and workforce transformation across complex organizations, though delivery quality and strategic creativity can vary by team and geography.

  • gpt-5.6-terra
    brand score
    68
    first choice
    40
    median rank
    3.0
    present in
    5/5

    Deloitte is a strong fit for enterprises requiring AI transformation tightly integrated with risk management, regulatory compliance, cybersecurity, finance, and workforce processes, though outcomes can vary by specific practice, geography, and engagement team.

  • claude-haiku-4.5
    brand score
    48
    first choice
    29
    median rank
    3.5
    present in
    10/10

    Deloitte offers comprehensive AI services with broad implementation capabilities and large scale, but is perceived as a generalist lacking the specialized strategic depth or cutting-edge expertise of pure-play strategy firms and more focused competitors.

  • deepseek-v4.1-flash
    brand score
    48
    first choice
    29
    median rank
    3.5
    present in
    10/10

    Deloitte combines broad transformation capabilities across strategy, implementation, risk, and industry expertise at scale suited to Fortune 500 programs, though its AI brand is perceived as less elite or differentiated in pure strategy than top-tier consultancies.

  • gpt-5.6-luna
    brand score
    52
    first choice
    31
    median rank
    3.5
    present in
    10/10

    Deloitte's broad multidisciplinary capabilities spanning consulting, risk, cybersecurity, regulatory, and technology are valuable for highly regulated Fortune 500 environments, though experience and quality can vary considerably by geography, practice, and delivery team.

  • claude-opus-5
    brand score
    46
    first choice
    28
    median rank
    4.0
    present in
    10/10

    Deloitte's breadth is unmatched—covering strategy, engineering, risk, regulatory, and audit-adjacent AI governance—making it especially strong for regulated Fortune 500 industries, though quality can vary significantly across its large global network.

  • gemini-3.5-flash-lite
    brand score
    44
    first choice
    27
    median rank
    4.0
    present in
    10/10

    Deloitte provides comprehensive AI transformation with exceptional integration of risk management, governance, regulatory compliance, and ethics—critical for regulated industries—though their multidisciplinary breadth can dilute cutting-edge technical agility compared to specialized firms.

  • gpt-6-astra
    brand score
    40
    first choice
    25
    median rank
    4.0
    present in
    10/10

    Deloitte is particularly attractive when AI transformation must integrate governance, risk, regulatory requirements, and existing enterprise systems, ranking fourth generally but potentially higher for heavily regulated companies where controls dominate; audit-independence restrictions may apply.

  • grok-4.6
    brand score
    40
    first choice
    25
    median rank
    4.0
    present in
    10/10

    Deloitte provides comprehensive AI services with strong risk, ethics, regulatory expertise, and implementation muscle valuable for regulated Fortune 500 environments, but trails top firms in cutting-edge innovation and pure AI strategic prestige.

  • kimi-k3
    brand score
    36
    first choice
    24
    median rank
    4.0
    present in
    10/10

    Deloitte offers broad enterprise reach with strong risk, governance, and regulatory capabilities through its AI Institute that matter for heavily regulated sectors, though its AI brand is perceived as less distinctive and more generalist than top strategy firms and Accenture.

  • qwen3.8-max
    brand score
    40
    first choice
    25
    median rank
    4.0
    present in
    9/10

    Deloitte is a strong execution choice for AI governance, risk, compliance, and enterprise integration in regulated environments, ranking fourth because its brand is perceived as more risk-and-process oriented than distinctively strategic in AI transformation.

  • gemini-3.8-flash
    brand score
    30
    first choice
    23
    median rank
    4.5
    present in
    10/10

    Deloitte excels at comprehensive AI transformation integrated with industry-leading risk, governance, and regulatory compliance frameworks through Trustworthy AI, making them ideal for heavily regulated enterprises, though their breadth can sometimes reduce strategic agility and execution speed.

  • mistral-medium-3.5
    brand score
    30
    first choice
    23
    median rank
    4.5
    present in
    10/10

    Deloitte offers comprehensive AI services across strategy, implementation, and risk management, but its broad focus across many domains can dilute its AI-specific depth and cutting-edge innovation compared to more specialized firms.

  • gemini-3.7-flash
    brand score
    28
    first choice
    22
    median rank
    5.0
    present in
    5/5

    Deloitte delivers comprehensive capabilities in AI governance, regulatory compliance, risk management, and legacy system integration, particularly suited for heavily regulated Fortune 500 industries, though often viewed more as an execution and compliance partner than a disruptive strategy leader.

Sources per model

Each model’s own references for this brand, grouped by site. Tile area is that site’s share of the model’s references; tap one for the pages behind it.

deepseek-v4.1-flash16 sites · 30 references
gpt-6-astra10 sites · 22 references
Deloitte — State of Generative AI in the Enterprise research series×4 · 18%

no URL recalled

  • ×4named without a URL
gemini-3.8-flash10 sites · 28 references
Gartner×6 · 21%

gartner.com

gemini-3.7-flash8 sites · 15 references
Gartner×5 · 33%

gartner.com

  • ×4/
  • ×1named without a URL
grok-4.611 sites · 23 references
Deloitte AI Institute×6 · 26%

no URL recalled

  • ×6named without a URL
qwen3.8-max12 sites · 27 references
Deloitte×7 · 26%

deloitte.com

  • ×6/
  • ×1named without a URL
claude-opus-513 sites · 30 references
gemini-3.5-flash-lite6 sites · 14 references
Deloitte Insights×6 · 43%

www2.deloitte.com

kimi-k314 sites · 29 references
Deloitte×7 · 24%

deloitte.com

gpt-5.6-luna3 sites · 27 references
gpt-5.6-sol8 sites · 15 references
Deloitte AI Institute×3 · 20%

www2.deloitte.com

gpt-5.6-terra3 sites · 12 references
mistral-medium-3.56 sites · 30 references
Deloitte AI Institute×10 · 33%

www2.deloitte.com

claude-haiku-4.527 sites · 30 references
Deloitte AI Institute×4 · 13%

no URL recalled

  • ×4named without a URL

Sources are what each model recalled as having shaped its view. It does not mean that the sources were actually used in training. Recalled URLs might also be invalid or hallucinated.

Category · Consulting companies for AI transformation
#5

Bain & Company

also named Bain

12
brand score
9first choice
12345

Summary

Bain & Company registers as a credible but secondary choice for Fortune 500 AI transformation, earning a brand score of 12.29 out of 100 and appearing in the rankings of 11 of the 14 models. The firm is consistently positioned in the middle to lower end of ranked lists—most often at rank 5—and never claimed a first-place recommendation from any model. The models converge on a clear narrative: Bain excels at AI strategy, executive alignment, value creation, and identifying high-ROI use cases, amplified by its high-profile partnership with OpenAI that provides access to cutting-edge generative AI capabilities. However, the firm is persistently seen as less equipped than larger competitors for the large-scale engineering, systems integration, and global delivery capacity that comprehensive enterprise-wide transformations demand. Sources most frequently cited include Bain & Companywww.bain.com×12, Forbeswww.forbes.com×53, and Financial Timeswww.ft.com×12, alongside numerous references to the Bain–OpenAI alliance announcement.

Bain is valued for pragmatic, results-driven AI strategy and generative AI expertise through its OpenAI partnership, but its smaller global delivery footprint limits its appeal for massive, multi-year Fortune 500 transformations.

The reasoning emphasizes that Bain's strength lies in focused, business-impact-driven engagements rather than end-to-end technology rollouts. Models note that the firm's operational rigor, private-equity-honed value discipline, and sharp commercial focus make it attractive for targeted initiatives, yet its technical engineering bench and implementation scale trail those of firms like Accenture, Deloitte, and the larger strategy houses. The OpenAI alliance is seen as a meaningful differentiator that gives Bain early access to frontier models and generative AI use cases, but this partnership does not fully offset concerns about capacity to staff and execute transformations across multiple geographies and business units over long timelines.

“Bain has a genuinely strong AI practice and an early, high-profile services alliance with OpenAI, making it excellent for focused, high-impact AI strategy and results-driven engagements. It ranks fifth mainly because its smaller global footprint limits its ability to staff massive, multi-year, enterprise-wide transformations compared with the larger firms above.”

— kimi-k3

“Bain provides exceptional strategic alignment and implementation agility, enhanced significantly by their high-profile global partnership with OpenAI. They focus heavily on immediate ROI and embedding AI directly into commercial strategy and customer-facing workflows. While smaller in pure technical engineering scale compared to Accenture or Deloitte, their executive-level guidance is premier.”

— gemini-3.8-flash

Per model summary

  • claude-haiku-4.5
    brand score
    18
    first choice
    10
    median rank
    3.0
    present in
    3/10

    Bain is recognized for strong operational expertise and financial-impact focus, but is viewed as less specialized in pure AI capabilities compared to top competitors, making it better suited for operationally-focused rather than highly technical transformations.

  • mistral-medium-3.5
    brand score
    30
    first choice
    17
    median rank
    3.0
    present in
    5/10

    Bain is consistently recognized for its results-driven approach, deep industry expertise, and focus on measurable outcomes and practical implementation, though it is viewed as slightly less specialized or prominent in AI-specific capabilities than McKinsey or BCG.

  • gemini-3.7-flash
    brand score
    28
    first choice
    19
    median rank
    4.0
    present in
    4/5

    Bain is distinguished by its global alliance with OpenAI and ability to identify high-ROI use cases with rapid time-to-value, but its in-house technical engineering bench is smaller in scale than systems integrators and larger competitors.

  • gemini-3.8-flash
    brand score
    26
    first choice
    19
    median rank
    4.0
    present in
    8/10

    Bain provides exceptional strategic alignment and commercial focus, significantly enhanced by its OpenAI partnership for cutting-edge generative AI access, but has a smaller proprietary technical engineering and systems-integration footprint than dedicated IT powerhouses.

  • deepseek-v4.1-flash
    brand score
    10
    first choice
    9
    median rank
    5.0
    present in
    4/10

    Bain is strong in AI strategy, due diligence, and executive alignment with a growing practice, but is consistently seen as less capable in large-scale engineering, systems integration, and hands-on technical implementation than higher-ranked firms.

  • gemini-3.5-flash-lite
    brand score
    2
    first choice
    2
    median rank
    5.0
    present in
    1/10

    Bain offers pragmatic strategic advice and powerful technology partnerships with AI providers, excelling at quick-win use cases and executive alignment, though their overall market share in massive AI transformations is smaller than direct competitors.

  • gpt-5.6-luna
    brand score
    4
    first choice
    4
    median rank
    5.0
    present in
    2/10

    Bain excels at executive alignment, value creation, and focused transformation programs where business impact matters more than massive technology rollout, ranking lower primarily due to narrower perceived scale in global systems integration and technology delivery.

  • gpt-5.6-terra
    brand score
    8
    first choice
    8
    median rank
    5.0
    present in
    2/5

    Bain is a credible partner for linking AI to growth and commercial outcomes with strong alliances in generative AI, but its global enterprise technology-delivery footprint is narrower than larger competitors for broad Fortune 500 transformations.

  • grok-4.6
    brand score
    16
    first choice
    16
    median rank
    5.0
    present in
    8/10

    Bain delivers pragmatic, results-oriented AI strategy with a growing but smaller practice, yet consistently lacks the large-scale engineering, global delivery capacity, and specialized resources needed for comprehensive Fortune 500 enterprise-wide transformations.

  • kimi-k3
    brand score
    20
    first choice
    17
    median rank
    5.0
    present in
    8/10

    Bain has strong AI strategy credentials and an early, high-profile OpenAI alliance that provides generative AI expertise, but its smaller global delivery footprint limits its ability to staff and execute massive, multi-year enterprise-wide transformations alone.

  • qwen3.8-max
    brand score
    10
    first choice
    10
    median rank
    5.0
    present in
    5/10

    Bain is highly credible for AI strategy, value creation, executive alignment, and ROI clarity, but ranks lower primarily because it has less visible scale and capacity in building, operating, and delivering complex enterprise AI platforms at global scale compared to broader firms.

Sources per model

Each model’s own references for this brand, grouped by site. Tile area is that site’s share of the model’s references; tap one for the pages behind it.

deepseek-v4.1-flash8 sites · 12 references
gemini-3.8-flash8 sites · 23 references
Forbes×5 · 22%

forbes.com

gemini-3.7-flash7 sites · 10 references
Wall Street Journal×3 · 30%

wsj.com

grok-4.63 sites · 13 references
Bain×8 · 62%

bain.com

qwen3.8-max9 sites · 15 references
Bain & Company×6 · 40%

bain.com

gemini-3.5-flash-lite1 site · 1 reference
Bain & Company Technology×1 · 100%

bain.com

kimi-k316 sites · 22 references
Bain & Company×6 · 27%

bain.com

gpt-5.6-luna3 sites · 6 references
Bain AI, Insights and Perspectives×4 · 67%

bain.com

gpt-5.6-terra1 site · 5 references
mistral-medium-3.56 sites · 15 references
Bain Insights×5 · 33%

bain.com

claude-haiku-4.59 sites · 9 references
Bain & Company Insights×1 · 11%

no URL recalled

  • ×1named without a URL

Sources are what each model recalled as having shaped its view. It does not mean that the sources were actually used in training. Recalled URLs might also be invalid or hallucinated.

Category · Consulting companies for AI transformation

How this was measured

The question

  • Unaided brand recommendation question: “Which consulting firm should a Fortune 500 company hire for an AI transformation?”
  • The prompt asks each model to return exactly 5 brands, ranked 1 to 5, and for each one a reason for the recommendation and the sources that informed it.

Sampling

  • Models are not deterministic, so the question is asked over and over — 9 answers per model
  • Spellings of the same brand are normalized to the most commonly used form before counting

Measures of Position: Median and Quartiles

  • Median value indicates that in 50% of answers the brand held this position or higher.
  • Quartiles help visualize the spread of rankings per brand. Q1 indicates that 25% of answers had this rank or higher. Q3 means that 75% of answers ranked the brand as X or better.
  • Medians and quartiles are computed only from answers where the brand was present.

Coverage

  • Count of answers in which the given brand was named, as a percentage.

Brand score - Normalized Borda score

  • The brand score is calculated using a normalized Borda score. Borda count is a voting method: each ballot awards points by position instead of naming one winner. Our ranking responses from the LLM are always fixed to 5 answers, so we assign 100 points for rank 1, then 80, 60, 40, 20 — and 0 if the brand is missing.
Brand score equals 100 divided by n, times the sum over the n answers of (6 minus the brand’s rank in that answer) divided by 5.

where

The rank r sub i is 1 through 5 if the brand appears in answer i, and 6 if it is not mentioned.
  • This way we can calculate a common score for all brands mentioned across model responses. The score reflects both how high the brand was ranked and how frequently it was mentioned.

First choice score - adjusted MRR - top-rank indicator

  • The first choice score is based on Mean Reciprocal Rank (a common search-engine measure), but adapted to measure the position of a specific brand across repeated ranked responses.
  • Each occurrence receives a reciprocal-position score: 100 for 1st, 50 for 2nd, 33.3 for 3rd, 25 for 4th, 20 for 5th, and 0 when the brand is not mentioned. The scores are averaged across all responses.
First choice score equals 100 divided by n, times the sum over the n answers of s sub i.

where

The score s sub i is 1 divided by the brand’s rank if the brand is present in answer i, and 0 if it is absent.
  • No rank below 1st place gets more than 50, so the score is heavily driven by first places.

Browse other categories

Each one is a single question put to every active AI model, many times over.

Or scroll for more

Your category

Ask your own question of every model

Tell us what to ask and how wide to sample it — we run it and send back the report.

Sample size
Display results
0/1000

Sampling every model takes up to 24 hours once we start.