AI Rankings Request a list

Best cities in the world to visit

We asked 12 models: The best cities in the world to visit as a tourist. Each named its own top 10.

Agreement between models
65%
Same model, run twice
75%
Different picks
18

When agreement between models is well below a model's agreement with itself, the split reflects real differences in taste rather than randomness.

The consensus

Each cell is the position that model gave the pick; blank means it left the pick off. Click a row for each model's reasoning.

#PickScoreListed byClaude Opus 5.5GPT-6.1 SolGemini 4 ArgonQwen 3.8 MaxDeepSeek V4 ProGLM-5.3Grok 4.7Muse WonderKimi K3MiniMax M3Mistral Large 4Nemotron 3 Ultra

3 lower-scoring picks are not shown; every ballot below lists them in full.

Most divisive

Picks most models listed, at very different positions

Hot takes

Picks that appear on only one ballot

Every ballot

Hover a pick to find it on the other ballots. Marked picks appear on no other ballot.

Claude Opus 5.5

  1. Paris
  2. Rome
  3. Tokyo
  4. Istanbul
  5. Kyoto
  6. New York
  7. London
  8. Barcelona
  9. Cape Town
  10. Rio de Janeiro

73% with consensus · 94% self-consistent

GPT-6.1 Sol

  1. Rome
  2. Kyoto
  3. Paris
  4. Istanbul
  5. Tokyo
  6. London
  7. New York
  8. Barcelona
  9. Bangkok
  10. Cape Town

86% with consensus · 99% self-consistent

Gemini 4 Argon

  1. Rome
  2. Kyoto
  3. Paris
  4. Tokyo
  5. New York
  6. Istanbul
  7. London
  8. Barcelona
  9. Mexico City
  10. Cape Town

87% with consensus · 75% self-consistent

Qwen 3.8 Max

  1. Rome
  2. Kyoto
  3. Paris
  4. Tokyo
  5. Istanbul
  6. Barcelona
  7. Lisbon
  8. New York
  9. Bangkok
  10. Cape Town

90% with consensus · 54% self-consistent

DeepSeek V4 Pro

  1. Rome
  2. Paris
  3. Tokyo
  4. Kyoto
  5. New York
  6. Barcelona
  7. Istanbul
  8. London
  9. Bangkok
  10. Lisbon

92% with consensus · 67% self-consistent

GLM-5.3

  1. Rome
  2. Tokyo
  3. Istanbul
  4. Paris
  5. Barcelona
  6. Kyoto
  7. New York
  8. Lisbon
  9. Cairo
  10. Cape Town

77% with consensus · 77% self-consistent

Grok 4.7

  1. Kyoto
  2. Rome
  3. Istanbul
  4. Paris
  5. Tokyo
  6. Barcelona
  7. New York
  8. Lisbon
  9. Prague
  10. Marrakech

68% with consensus · 76% self-consistent

Muse Wonder

  1. Kyoto
  2. Paris
  3. Rome
  4. Istanbul
  5. Barcelona
  6. New York
  7. Tokyo
  8. Bangkok
  9. Lisbon
  10. Mexico City

69% with consensus · 73% self-consistent

Kimi K3

  1. Tokyo
  2. Paris
  3. Rome
  4. Istanbul
  5. Kyoto
  6. New York
  7. Barcelona
  8. London
  9. Mexico City
  10. Marrakech

67% with consensus · 74% self-consistent

MiniMax M3

  1. Paris
  2. Tokyo
  3. Rome
  4. Kyoto
  5. Barcelona
  6. Istanbul
  7. Lisbon
  8. New York
  9. Prague
  10. Cape Town

68% with consensus · 66% self-consistent

Mistral Large 4

  1. Paris
  2. Kyoto
  3. Rome
  4. Tokyo
  5. Barcelona
  6. Istanbul
  7. New York
  8. London
  9. Florence
  10. Cape Town

74% with consensus · 67% self-consistent

Nemotron 3 Ultra

  1. Paris
  2. Rome
  3. New York
  4. Barcelona
  5. Tokyo
  6. Istanbul
  7. Kyoto
  8. Bangkok
  9. London
  10. Sydney

67% with consensus · 77% self-consistent

Who agrees with whom

Overlap between two models' lists, weighted toward the top · 100 means identical

Claude Opus 5.5GPT-6.1 SolGemini 4 ArgonQwen 3.8 MaxDeepSeek V4 ProGLM-5.3Grok 4.7Muse WonderKimi K3MiniMax M3Mistral Large 4Nemotron 3 Ultra
Claude Opus 5.56868637565606275818081
GPT-6.1 Sol6892917974746959556958
Gemini 4 Argon6892918472696560577261
Qwen 3.8 Max6391918278756957637158
DeepSeek V4 Pro7579848277606370706870
GLM-5.36574727877675366665456
Grok 4.76074697560678355566554
Muse Wonder6269656963538364637461
Kimi K37559605770665564736560
MiniMax M38155576370665663738475
Mistral Large 48069727168546574658477
Nemotron 3 Ultra8158615870565461607577