Benchmark LLM-iek

Rovnaký GTA prompt, sedem modelov.

Modely dostali rovnaké náročné zadanie: vytvoriť v prehliadači 3D open-world mesto inšpirované Miami s autami, chodcami, políciou, misiami a syntetizovaným zvukom. Claude Fable 5 je hrateľný; Claude Opus 5, GPT-5.6 Sol a GPT-5.5 sú čiastočne hrateľné. Aj najlepšie výsledky majú chyby; ostatné výstupy majú veľmi veľa chýb a sú nehrateľné.

Výsledkov
7
Hrateľných alebo čiastočne
5
Dostupných dem
7
Metóda
Rovnaký prompt

Kompletné poradie

Výsledky a hrateľné demá

Predvolené poradie vychádza z praktického výsledku. Filtre nemenia poradie, iba skrývajú nezodpovedajúce modely.

Filtrovanie
Hrateľnosť
Typ
Parametre
Poradie GTA benchmarku Subjektívne poradie podľa praktického výsledku v tomto benchmarku
Náhľad Model Typ Parametre / pamäť** Výsledok Chyby Poznámka Demo
Gameplay screenshot GTA hry BAYSIDE vygenerovanej modelom Claude Fable 5 1Claude Fable 5 Uzavretý - Splnil zadanie Hrateľný Veľa chýb 1 opravný prompt. Generovanie približne 1 h 20 min; takmer 400K kontext. Demo
Gameplay screenshot GTA hry Neon Bay vygenerovanej modelom Claude Opus 5 2Claude Opus 5 Uzavretý - Splnil zadanie čiastočne Čiastočne hrateľný Veľmi veľa chýb 1 opravný prompt na ovládanie. Demo
Náhľad GTA hry Neon Palms vygenerovanej modelom GPT-5.6 Sol 3GPT-5.6 Sol Uzavretý - Splnil zadanie čiastočne Čiastočne hrateľný Veľmi veľa chýb Vyžadoval 2 opravné prompty na ovládanie. Demo
Gameplay screenshot GTA hry vygenerovanej modelom GPT-5.5 4GPT-5.5 Uzavretý - Splnil zadanie čiastočne Čiastočne hrateľný Veľmi veľa chýb - Demo
Gameplay screenshot GTA hry vygenerovanej modelom Gemini 3.5 Flash 5Gemini 3.5 Flash Uzavretý - Splnil zadanie čiastočne Nehrateľný Veľmi veľa chýb - Demo
Gameplay screenshot GTA hry vygenerovanej modelom GLM 5.2 6GLM 5.2 Otvorené váhy (OpenRouter) 744B (40B aktívnych) 416 GB - 816 GB Splnil zadanie čiastočne Nehrateľný Veľmi veľa chýb - Demo
Gameplay screenshot GTA hry vygenerovanej modelom Qwen 3.6 27B ThinkingCap 7Qwen 3.6 27B ThinkingCap Otvorené váhy 27B 18 GB - 50 GB Zadanie nesplnil Nefungoval Obsahuje fatálne chyby Žiaden viditeľný svet.
Generovanie približne 1 h 17 min.
Demo

**Pamäť je iba orientačný odhad pre Q4 váhy: prvá hodnota je odhad pri 0K kontexte, druhá pri 100K kontexte. Nie je to meranie ani presný výpočet konkrétnej architektúry.

Na mobile alebo tablete tlačidlo Demo otvorí website-owned wrapper s dotykovým ovládaním. Pôvodný benchmark kód ostáva nezmenený.

Gameplay screenshot GTA hry BAYSIDE vygenerovanej modelom Claude Fable 5

1Claude Fable 5

Uzavretý
Parametre / pamäť**
-
Výsledok
Splnil zadanie Hrateľný
Chyby
Veľa chýb
Poznámka
1 opravný prompt. Generovanie približne 1 h 20 min; takmer 400K kontext.
Demo
Gameplay screenshot GTA hry Neon Bay vygenerovanej modelom Claude Opus 5

2Claude Opus 5

Uzavretý
Parametre / pamäť**
-
Výsledok
Splnil zadanie čiastočne Čiastočne hrateľný
Chyby
Veľmi veľa chýb
Poznámka
1 opravný prompt na ovládanie.
Demo
Náhľad GTA hry Neon Palms vygenerovanej modelom GPT-5.6 Sol

3GPT-5.6 Sol

Uzavretý
Parametre / pamäť**
-
Výsledok
Splnil zadanie čiastočne Čiastočne hrateľný
Chyby
Veľmi veľa chýb
Poznámka
Vyžadoval 2 opravné prompty na ovládanie.
Demo
Gameplay screenshot GTA hry vygenerovanej modelom GPT-5.5

4GPT-5.5

Uzavretý
Parametre / pamäť**
-
Výsledok
Splnil zadanie čiastočne Čiastočne hrateľný
Chyby
Veľmi veľa chýb
Poznámka
-
Demo
Gameplay screenshot GTA hry vygenerovanej modelom Gemini 3.5 Flash

5Gemini 3.5 Flash

Uzavretý
Parametre / pamäť**
-
Výsledok
Splnil zadanie čiastočne Nehrateľný
Chyby
Veľmi veľa chýb
Poznámka
-
Demo
Gameplay screenshot GTA hry vygenerovanej modelom GLM 5.2

6GLM 5.2

Otvorené váhy (OpenRouter)
Parametre / pamäť**
744B (40B aktívnych) 416 GB - 816 GB
Výsledok
Splnil zadanie čiastočne Nehrateľný
Chyby
Veľmi veľa chýb
Poznámka
-
Demo
Gameplay screenshot GTA hry vygenerovanej modelom Qwen 3.6 27B ThinkingCap

7Qwen 3.6 27B ThinkingCap

Otvorené váhy
Parametre / pamäť**
27B 18 GB - 50 GB
Výsledok
Zadanie nesplnil Nefungoval
Chyby
Obsahuje fatálne chyby
Poznámka
Žiaden viditeľný svet.
Generovanie približne 1 h 17 min.
Demo

Metodika

Zadanie použité na porovnanie

Prompt je zachovaný v pôvodnom znení. Hodnotenie vychádza z reálneho spustenia, hrateľnosti, chýb a obmedzení konkrétneho výstupu.

Prompt použitý na zadanie

Create a 3D open-world action game inspired by classic GTA-style gameplay. The game should have a stylized visual style close to GTA: San Andreas, but with improved graphics, better lighting, more detailed environments, and smoother animations. Do not use copyrighted GTA assets, names, characters, maps, or exact copies; create an original game with a similar open-world crime-action feeling.

The game should use a third-person camera. The player must be able to walk, run, sprint, fight in melee combat, shoot different types of weapons, and interact with vehicles. Weapons should be placed in various harder-to-reach locations across the map, or the player should be able to obtain them from armed gangsters or police officers after defeating them.

The player must be able to enter cars, steal cars, pull drivers out of vehicles, and drive around the city. The city should be inspired by Miami, with a tropical coastal atmosphere, boats, the sea, canals, bridges, beaches, hotels, highways, and dense urban districts.

The map should be fairly large and should not be a simple square grid. The road layout should include streets of different shapes, curves, alleys, intersections, multi-level intersections, bridges, tunnels, and a highway network with exits leading into city streets. The city should contain different districts with different architecture, atmosphere, culture, population density, and types of people, similar to real American cities.

Include districts such as:

* a Chinatown-style district,
* a Hispanic district,
* a district with a larger African-American community,
* a wealthy residential district,
* a downtown district with high-rise buildings,
* office districts with business buildings,
* coastal hotel areas with balconies, pools, bars, tourists, and people relaxing,
* dangerous gang-controlled districts,
* and one district occupied by homeless people living in tents.

The beach areas should be full of life. There should be people swimming, sunbathing, playing beach volleyball, walking, talking, skating, rollerblading, cycling, and relaxing near the sea. Streets in different districts should have different population densities, and pedestrians should visually and behaviorally match the district they are in.

Some dangerous districts should be controlled by gangs. Gangs should be visually recognizable by their clothing, colors, behavior, and preferred weapons. Gang members should patrol their areas, react aggressively to threats, and sometimes attack the player if provoked.

Create a custom map-generation format and tool for building the city. Think of it like a simplified SimCity-style internal format that describes roads, buildings, parks, parking lots, beaches, canals, bridges, highways, districts, spawn zones, and other city components. Use this format to generate repeated but varied patterns of buildings, roads, parks, parking lots, sidewalks, props, and environmental details. The city should feel handcrafted but should be generated from reusable rules and templates.

On the edge of the city, include an airport where planes can land and take off. The airport should have runways, hangars, parked vehicles, security areas, and moving aircraft.

The city should include civilians, gang members, police officers, police cars, police motorcycles, and two police helicopters. Police officers should appear as pedestrians, motorcycle officers, and drivers of police vehicles. The police should only start chasing the player when they witness the player committing a crime, such as shooting in the street, attacking civilians, stealing cars, or causing serious destruction. Police should not be everywhere; they should be distributed naturally so that the player is not immediately chased after the first small incident unless police are nearby and actually notice it.

Civilians should have different personalities and reactions. Most people should panic and run away when the player starts shooting, attacks someone, or tries to steal a car. Some drivers should panic and quickly drive away if the player tries to steal their vehicle but is too slow. A smaller number of civilians should be brave or aggressive and may fight back if the player attacks them, damages their car, or tries to steal their vehicle. However, if the player starts shooting, even these braver civilians should try to escape.

In dangerous districts, include dealers offering strange substances that can temporarily cause altered visual effects, distorted controls, hallucination-like effects, or other weird states for the player. These districts may also include prostitutes, addicts, and other street characters to make the atmosphere feel darker and more dangerous. Also include bars where the player can get drunk and where regular customers hang out, talk, argue, or react to the player.

The game should include classic GTA-style missions, but they should not feel repetitive. Each mission should be slightly different. Add around 20–30 missions in total. Mission types can include:

* delivering cargo from point A to point B,
* assassinating a gang leader,
* stealing a car full of money,
* winning illegal street races,
* escaping police during a race,
* finding and eliminating a rat cooperating with the police,
* protecting a character,
* attacking a gang hideout,
* stealing weapons,
* escaping by boat through canals,
* chasing a target through traffic,
* and other open-world crime-action mission types.

The game should include a mission system with objectives, markers, failure conditions, success conditions, rewards, and mission progression. Missions should use different vehicles, locations, enemies, and situations so that they do not feel copied from each other.

Add sounds for everything important:

* car engines,
* horns,
* brakes,
* crashes,
* tires,
* boats,
* helicopters,
* airplanes,
* footsteps,
* punches,
* gunfire,
* explosions,
* people talking,
* frightened civilians screaming,
* angry civilians shouting,
* police sirens,
* gang threats,
* bar ambience,
* beach ambience,
* city traffic,
* ocean waves,
* and general city noise.

Because this is a large and demanding task, plan it carefully before implementation. First create a dedicated TODO.md file. In TODO.md, break the whole project into clear milestones and smaller tasks. Then complete the work step by step, following the TODO.md file point by point. Keep updating TODO.md as tasks are completed. Do not skip details. Build the game gradually, starting with the core playable systems, then the city, traffic, pedestrians, police, gangs, missions, sound, UI, and final polish.