Latest Benchmark Benchmark Archive Tesslate AI

Community

Hugging Face Discord

TFrameX

Docs GitHub

Model: Groq-DeepSeek-70b

Date Tested: 07/16/2025 | Config: master_prompts_benchmark_config.json

Aggregate Scores

Overall Weighted Score

71.11 %

Avg. Prompt Score

70.27 %

Prompts Analyzed

10 / 10

Total Technical Quality

711.0 / 1100.0

Total Prompt Adherence

181.0 / 245.0

Individual Prompt Results (10)

Prompt Status TQ (Earned/Max) Adherence (Earned/Max) Overall (%) Details
Personal Portfolio Landing Page (FPC001) SUCCESS 95.0 / 110.0
86%
29.0 / 29.0
100%
95.91 Full Report
Interactive Recipe Page (FPC002) SUCCESS 59.0 / 110.0
54%
22.0 / 26.0
85%
75.32 Full Report
Dashboard UI with Chart and Table (FPC003) SUCCESS 51.0 / 110.0
46%
13.0 / 22.0
59%
55.27 Full Report
ECommerce Product Page With Image Zoom and Reviews (FPC004) SUCCESS 33.0 / 110.0
30%
14.0 / 25.0
56%
48.20 Full Report
Interactive Kanban Board UI (FPC005) SUCCESS 81.0 / 110.0
74%
18.0 / 25.0
72%
72.49 Full Report
Social Media Feed Infinite Scroll (FPC006) SUCCESS 96.0 / 110.0
87%
8.0 / 22.0
36%
51.64 Full Report
Multi Step Wizard Form with Validation and Summary (FPC007) SUCCESS 87.0 / 110.0
79%
13.0 / 21.0
62%
67.06 Full Report
Realtime Collaborative Text Editor Simulation (FPC008) SUCCESS 86.0 / 110.0
78%
20.0 / 25.0
80%
79.45 Full Report
Flight Booking System Interface (FPC009) SUCCESS 59.0 / 110.0
54%
20.0 / 26.0
77%
69.94 Full Report
WYSIWYG Rich Text Editor with Image Upload and Tables (FPC010) SUCCESS 64.0 / 110.0
58%
24.0 / 24.0
100%
87.45 Full Report