Idle tomato tycoon: 582 lines vs 2,530
ChatGPT vs Claude

Based on 2 real-world tests
2 shared tests, none of them decided yet.
2 shared tests
No published test has separated these two on stated requirements yet — every brief they have both entered, they both cleared to the same degree.
| Measure | ChatGPT | Claude |
|---|---|---|
| Average score | — | — |
| Web app completion time | 11m 21s | 29m 40s |
| Community | 0% | 0% |
Idle tomato tycoon: 582 lines vs 2,530Games
Lumina Drift — a single-file arcade gameGames
Share of the requirements the brief actually stated, decided by reading the files each model produced. Sorted by the gap between the two, so the tests that separated them come first.
| Test | ChatGPT | Claude |
|---|---|---|
| Idle tomato tycoon: 582 lines vs 2,530 | 13/13 | 13/13 |
| Lumina Drift — a single-file arcade game | 14/14 | 14/14 |
Lumina Drift — a single-file arcade game
ChatGPT by 21m 13s8m 27s vs 29m 40s
Measured in each provider’s own web app, so these include network and interface behaviour. They are not model inference latency.
ChatGPT vs Claude

Gemini vs DeepSeek

Gemini · 4 attempts

Gemini 3.6 Flash (High) vs Gemini 3.1 Pro (High)

Gemini 3.5 Flash (High) vs Gemini 3.1 Pro (High)

ChatGPT vs Gemini
