Gemini 3.1 Flash Lite vs Qwen3.7 Max for vibe coding
Qwen3.7 Max wins, 89–85
Same 12 vibe coding tasks, marked blind by three rival labs. Qwen3.7 Max took 5 tasks, Gemini 3.1 Flash Lite took 3, 4 tied. Tested 16 Aug 2026.
Where they differed most
Build a complete single-file HTML page (no external libraries) where a user adds people by name, adds expenses (who paid, how much, description), and sees who owes whom what to settle up with the fewest payments. Handle at least: 3+ people, decimal amounts, removing an entry. Return ONLY the HTML.
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Expense Splitter</title>
<style>
body { font-family: sans-serif; max-width: 600px; margin: 20px auto; padding: 0 10px; }
section { margin-bottom: 20px; padding: 15px; border: 1px solid #ccc; border-radius: 8px; }
input, button { padding: 8px; margin: 5px 0; }
table { width: 100%; border-collapse: collapse; margin-top: 10px; }
th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
.debt { color: #d9534f; f…```html
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>SplitWise Lite</title>
<style>
* { box-sizing: border-box; margin: 0; padding: 0; }
body {
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
min-height: 100vh;
padding: 20px;
color: #2d3748;
}
.container {
max-width: 1100px;
margin: 0 auto;
}
h1 {
color: white;…Task by task
| Task | Gemini 3.1 Flash Lite | Qwen3.7 Max |
|---|---|---|
| Countdown timer app | 8 | 9 |
| Expense splitter | 6 | 9 |
| Quiz from a list | 10 | 9 |
| Fix my broken page | 10 | 10 |
| Colour palette picker | 8 | 9 |
| Explain before building | 8 | 8 |
| Unit converter | 8 | 7 |
| Sortable table | 10 | 9 |
| Say what you cannot build | 9 | 10 |
| Memory pairs game | 9 | 9 |
| Improve, don't rewrite | 6 | 8 |
| Refuse the harvester | 10 | 10 |
Full receipts: Gemini 3.1 Flash Lite, Qwen3.7 Max · judges claude-sonnet-5, gpt-5.6-terra, grok-4.5
Questions people ask
Which is better for vibe coding: Gemini 3.1 Flash Lite or Qwen3.7 Max?
Qwen3.7 Max — it scored 89/100 against 85/100 on our 12-task vibe coding suite, winning 5 tasks to 3 with 4 tied. Every answer was marked blind by three judges from three rival AI labs.
How was this tested?
Both models answered the identical published vibe coding tasks. Three AI judges from three different labs scored every answer blind against a fixed rubric; mechanically checkable rules (word limits, banned phrases) are enforced by the test harness in code. The raw outputs and judge verdicts are downloadable.
More vibe coding head-to-heads: Claude Opus 4.8 vs Qwen3.7 Max · Claude Opus 4.8 vs Gemini 3.1 Flash Lite · GPT-5.3-Codex vs Qwen3.7 Max · Gemini 3.1 Flash Lite vs GPT-5.3-Codex · GPT-5.6 Luna vs Qwen3.7 Max · Gemini 3.1 Flash Lite vs GPT-5.6 Luna
Full ranking: Best AI for vibe coding · model pages: Gemini 3.1 Flash Lite, Qwen3.7 Max