Best US cities for a 30-year-old engineer

We asked 10 models: The best US cities to live in for a 30-year-old software engineer. Each named its own top 10.

Agreement between models

71%

Same model, run twice

85%

Different picks

16

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.

#	Pick	Score	Listed by	Claude Haiku 5.5	GPT-6 Luna	Gemini 4 Argon	Qwen 3.8 Flash	DeepSeek V4 Pro	GLM-5.3	Kimi K3	MiniMax M3	Mistral Large 4	Nemotron 3 Ultra
1	Seattle		10/10	1	1	1	2	1	1	2	1	2	2
2	Austin		10/10	3	4	2	1	2	3	1	3	1	4
3	San Francisco		10/10	2	2	3	9	3	2	5	2	7	1
4	Denver		10/10	4	7	5	3	5	4	3	4	3	6
5	Raleigh		10/10	7	8	7	4	6	6	4	7	4	7
6	Boston		10/10	5	5	6	6	9	7	7	5	5	5
7	New York		7/10	6	3	4		4	5		6		3
8	San Diego		7/10	8		9	5		9	6	8	6
9	Chicago		9/10	9	6	8	10	7	8	10		10	8
10	Portland		7/10				7	8	10	8	9	8	10
11	Atlanta		3/10			10					10		9
12	Minneapolis		2/10							9		9
13	Salt Lake City		1/10				8
14	Los Angeles		2/10		9			10
15	San Jose		1/10	10

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

Every ballot

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

Claude Haiku 5.5

1. Seattle
2. San Francisco
3. Austin
4. Denver
5. Boston
6. New York
7. Raleigh
8. San Diego
9. Chicago
10. San Jose

89% with consensus · 83% self-consistent

GPT-6 Luna

1. Seattle
2. San Francisco
3. New York
4. Austin
5. Boston
6. Chicago
7. Denver
8. Raleigh
9. Los Angeles
10. Washington

75% with consensus · 86% self-consistent

Gemini 4 Argon

1. Seattle
2. Austin
3. San Francisco
4. New York
5. Denver
6. Boston
7. Raleigh
8. Chicago
9. San Diego
10. Atlanta

92% with consensus · 92% self-consistent

Qwen 3.8 Flash

1. Austin
2. Seattle
3. Denver
4. Raleigh
5. San Diego
6. Boston
7. Portland
8. Salt Lake City
9. San Francisco
10. Chicago

68% with consensus · 88% self-consistent

DeepSeek V4 Pro

1. Seattle
2. Austin
3. San Francisco
4. New York
5. Denver
6. Raleigh
7. Chicago
8. Portland
9. Boston
10. Los Angeles

89% with consensus · 86% self-consistent

GLM-5.3

1. Seattle
2. San Francisco
3. Austin
4. Denver
5. New York
6. Raleigh
7. Boston
8. Chicago
9. San Diego
10. Portland

89% with consensus · 88% self-consistent

Kimi K3

1. Austin
2. Seattle
3. Denver
4. Raleigh
5. San Francisco
6. San Diego
7. Boston
8. Portland
9. Minneapolis
10. Chicago

72% with consensus · 77% self-consistent

MiniMax M3

1. Seattle
2. San Francisco
3. Austin
4. Denver
5. Boston
6. New York
7. Raleigh
8. San Diego
9. Portland
10. Atlanta

88% with consensus · 80% self-consistent

Mistral Large 4

1. Austin
2. Seattle
3. Denver
4. Raleigh
5. Boston
6. San Diego
7. San Francisco
8. Portland
9. Minneapolis
10. Chicago

70% with consensus · 79% self-consistent

Nemotron 3 Ultra

1. San Francisco
2. Seattle
3. New York
4. Austin
5. Boston
6. Denver
7. Raleigh
8. Chicago
9. Atlanta
10. Portland

63% with consensus · 94% self-consistent

Who agrees with whom

Overlap between two models' lists, weighted toward the top · 100 means identical · Color runs from 43 (lightest) to 98 (darkest)

	Claude Haiku 5.5	GPT-6 Luna	Gemini 4 Argon	Qwen 3.8 Flash	DeepSeek V4 Pro	GLM-5.3	Kimi K3	MiniMax M3	Mistral Large 4	Nemotron 3 Ultra
Claude Haiku 5.5		86	87	57	82	95	61	98	61	73
GPT-6 Luna	86		82	43	81	85	47	84	47	80
Gemini 4 Argon	87	82		60	95	88	64	86	62	70
Qwen 3.8 Flash	57	43	60		59	57	93	58	95	46
DeepSeek V4 Pro	82	81	95	59		87	65	82	61	67
GLM-5.3	95	85	88	57	87		62	94	59	73
Kimi K3	61	47	64	93	65	62		62	97	50
MiniMax M3	98	84	86	58	82	94	62		62	73
Mistral Large 4	61	47	62	95	61	59	97	62		50
Nemotron 3 Ultra	73	80	70	46	67	73	50	73	50