Benchmark Detail View
Parking Garage Management
HARD Challenge81 models testedTop Score: 67.1
Success Rate
42.0%
Quality Score
41
Tests Passed
16
Models Tested
81
Parking Garage Benchmark - Individual Model Results
Showing 81 of 81 models
1 Claude 3.7 Sonnet (Thinking) Claude • 08/2025 08/2025 | 67.1 | 69.2% |
2 DeepSeek V3 DeepSeek • 12/2025 12/2025 | 66.3 | 69.2% |
3 Grok 3 xAI • 08/2025 08/2025 | 65.9 | 69.2% |
4 Claude 4.6 Opus Claude • 02/2026 02/2026 | 65.9 | 69.2% |
5 Claude 4.5 Opus Claude • 11/2025 11/2025 | 64.3 | 69.2% |
6 Claude 4 Opus Claude • 08/2025 08/2025 | 64.1 | 69.2% |
7 DeepSeek V3 DeepSeek • 08/2025 08/2025 | 64.1 | 64.1% |
8 Claude 3.5 Sonnet Claude • 08/2025 08/2025 | 63.4 | 61.5% |
9 Claude 4 Sonnet Claude • 08/2025 08/2025 | 63.2 | 66.7% |
10 Claude 4.1 Opus Claude • 08/2025 08/2025 | 62.9 | 69.2% |
11 Claude 4.5 Sonnet Claude • 10/2025 10/2025 | 62.8 | 66.7% |
12 Codestral 25.08 Mistral • 08/2025 08/2025 | 60.6 | 61.5% |
13 Glm 4 6 Other • 10/2025 10/2025 | 60.0 | 61.5% |
14 DeepSeek V3 DeepSeek • 10/2025 10/2025 | 58.1 | 59.0% |
15 OpenAI GPT-4o OpenAI • 08/2025 08/2025 | 55.5 | 53.8% |
16 Devstral 2512 Other • 12/2025 12/2025 | 53.1 | 51.3% |
17 OpenAI GPT-5.2 Chat OpenAI • 12/2025 12/2025 | 51.8 | 51.3% |
18 OpenAI GPT-5 Chat OpenAI • 08/2025 08/2025 | 51.5 | 51.3% |
19 Gemini 3 Flash Google • 12/2025 12/2025 | 50.4 | 51.3% |
20 Qwen3 Max Alibaba • 10/2025 10/2025 | 50.3 | 53.8% |
21 Glm 4 7 Other • 12/2025 12/2025 | 50.1 | 51.3% |
22 Claude 3.7 Sonnet Claude • 08/2025 08/2025 | 49.1 | 51.3% |
23 OpenAI GPT-5.1 Chat OpenAI • 11/2025 11/2025 | 48.6 | 48.7% |
24 Kimi K2 Moonshot • 10/2025 10/2025 | 47.6 | 48.7% |
25 Horizon Beta Other • 08/2025 08/2025 | 47.3 | 48.7% |
26 OpenAI GPT-4.1 mini OpenAI • 08/2025 08/2025 | 46.7 | 46.2% |
27 OpenAI GPT-5 OpenAI • 09/2025 09/2025 | 46.6 | 48.7% |
28 OpenAI 5.2 Codex OpenAI • 01/2026 01/2026 | 46.5 | 51.3% |
29 OpenAI GPT-4.1 OpenAI • 08/2025 08/2025 | 46.3 | 48.7% |
30 OpenAI GPT-5 OpenAI • 08/2025 08/2025 | 45.5 | 48.7% |
31 R1 DeepSeek • 08/2025 08/2025 | 45.4 | 43.6% |
32 Llama 4 Scout Meta • 08/2025 08/2025 | 45.0 | 43.6% |
33 Qwen 3 Coder Alibaba • 10/2025 10/2025 | 44.9 | 46.2% |
34 Mistral Large 2512 Mistral • 12/2025 12/2025 | 44.8 | 43.6% |
35 OpenAI 5.1 Codex OpenAI • 11/2025 11/2025 | 44.7 | 41.0% |
36 OpenAI GPT-4o OpenAI • 08/2025 08/2025 | 44.4 | 43.6% |
37 Claude 4.5 Haiku Claude • 10/2025 10/2025 | 44.2 | 43.6% |
38 Kimi K2 Moonshot • 08/2025 08/2025 | 44.2 | 43.6% |
39 Mimo V2 Flash Free Other • 12/2025 12/2025 | 43.5 | 46.2% |
40 OpenAI GPT-5.2 OpenAI • 12/2025 12/2025 | 42.5 | 41.0% |
41 Kimi K2 Moonshot • 12/2025 12/2025 | 42.5 | 41.0% |
42 Llama 4 Maverick Meta • 08/2025 08/2025 | 42.5 | 41.0% |
43 OpenAI GPT-5.1 OpenAI • 11/2025 11/2025 | 42.2 | 43.6% |
44 Mistral Medium 3 Mistral • 08/2025 08/2025 | 41.6 | 38.5% |
45 OpenAI o3-mini OpenAI • 08/2025 08/2025 | 40.7 | 41.0% |
46 OpenAI GPT-4 Turbo OpenAI • 08/2025 08/2025 | 40.4 | 38.5% |
47 Qwen 3 Coder Alibaba • 08/2025 08/2025 | 40.3 | 41.0% |
48 OpenAI GPT-4 OpenAI • 08/2025 08/2025 | 39.8 | 38.5% |
49 Gemini 2.0 Flash-001 Google • 08/2025 08/2025 | 39.6 | 43.6% |
50 Sonoma Sky Alpha Other • 09/2025 09/2025 | 39.3 | 41.0% |
51 Grok 4 xAI • 08/2025 08/2025 | 39.2 | 38.5% |
52 OpenAI 5 Codex OpenAI • 10/2025 10/2025 | 38.9 | 41.0% |
53 Grok 4 xAI • 10/2025 10/2025 | 38.3 | 41.0% |
54 OpenAI o1-mini OpenAI • 08/2025 08/2025 | 37.1 | 35.9% |
55 OpenAI GPT-3.5 Turbo OpenAI • 08/2025 08/2025 | 36.4 | 33.3% |
56 Minimax M2 1 Other • 12/2025 12/2025 | 36.1 | 35.9% |
57 Claude 3 Haiku Claude • 08/2025 08/2025 | 36.0 | 33.3% |
58 Qwen3 14b Alibaba • 08/2025 08/2025 | 35.0 | 33.3% |
59 OpenAI o4-mini OpenAI • 08/2025 08/2025 | 32.9 | 30.8% |
60 OpenAI 5.1 Codex Mini OpenAI • 11/2025 11/2025 | 32.8 | 28.2% |
61 Grok Code Fast 1 xAI • 09/2025 09/2025 | 32.3 | 30.8% |
62 OpenAI o3-mini (High) OpenAI • 08/2025 08/2025 | 31.8 | 33.3% |
63 Openai Oss 20b OpenAI • 08/2025 08/2025 | 31.6 | 28.2% |
64 OpenAI GPT-5 mini OpenAI • 09/2025 09/2025 | 31.2 | 33.3% |
65 Gemini 3 Pro Preview Google • 11/2025 11/2025 | 30.1 | 30.8% |
66 Gemini 2.5 Flash Google • 08/2025 08/2025 | 29.7 | 30.8% |
67 OpenAI GPT-5 nano OpenAI • 08/2025 08/2025 | 29.0 | 28.2% |
68 OpenAI GPT-5 mini OpenAI • 08/2025 08/2025 | 28.9 | 30.8% |
69 OpenAI o4-mini (High) OpenAI • 08/2025 08/2025 | 27.9 | 25.6% |
70 Nova Micro V1 Amazon • 08/2025 08/2025 | 27.0 | 23.1% |
71 Nova Lite V1 Amazon • 08/2025 08/2025 | 23.8 | 17.9% |
72 Gemini 2.5 Pro Google • 08/2025 08/2025 | 23.5 | 20.5% |
73 Grok 3 Mini xAI • 08/2025 08/2025 | 23.4 | 23.1% |
74 OpenAI GPT-5 nano OpenAI • 09/2025 09/2025 | 22.7 | 20.5% |
75 Openai Oss 120b OpenAI • 08/2025 08/2025 | 20.4 | 17.9% |
76 Gemini 2.5 Flash Lite Google • 08/2025 08/2025 | 19.1 | 20.5% |
77 OpenAI GPT-4o mini OpenAI • 08/2025 08/2025 | 19.0 | 15.4% |
78 Claude 3.5 Haiku Claude • 08/2025 08/2025 | 16.9 | 12.8% |
79 Nova Pro V1 Amazon • 08/2025 08/2025 | 14.6 | 10.3% |
80 OpenAI GPT-4.1 nano OpenAI • 08/2025 08/2025 | 11.9 | 12.8% |
81 Coder Large Other • 08/2025 08/2025 | 9.3 | 7.7% |
Top Performers
#1
Claude67.1
Claude 3.7 Sonnet (Thinking)
Success Rate
69.2%27
Tests Passed
Q
48
Quality
26
Issues
39 total tests
#2
DeepSeek66.3
DeepSeek V3
Success Rate
69.2%27
Tests Passed
Q
40
Quality
30
Issues
39 total tests
#3
xAI65.9
Grok 3
Success Rate
69.2%27
Tests Passed
Q
36
Quality
32
Issues
39 total tests
Explore More Benchmarks
See how models perform across different programming challenges and complexity levels.