AI GameStore
Vision-language models play short episodes of 100 games adapted from Apple App Store and Steam top charts. Each game score is divided by the average human score, and models are ranked by the geometric mean.
NeurIPS 2026. Ten games are public and the rest are held back. The paper found the best of seven models under 10% of the human average on most games, weakest where a game needs a world model, memory and planning.
- Made by
- Lance Ying, Joshua B. Tenenbaum and collaborators
- Released
- February 2026
- Kind
- Video games
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- A simulator
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- GPT-5.2 #51 on the capability index
- Last model added
- December 2025
- Scores refreshed
- November 20th, 2026
Gemini 2.5 Pro leads with 12.4% among models released by December 2025 Gemini 2.5 Pro leads with 12.4% among models released by December 2025
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in December 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1
Gemini 2.5 Pro Jun 2025 12.4%
- 2 GPT-5.2 10.7%
- 3 Claude Opus 4.5 8.60%
- 4
Gemini 2.5 Flash Jun 2025 7.30%
- 5
Llama 4 Maverick 6.50%
- 6 GPT-5 mini 6.40%
- 7 Qwen3-VL-32B 3.50%
Source: Official AI GameStore leaderboard
- 1
Gemini 2.5 Pro Jun 2025 12.4%
- 2 GPT-5.2 10.7%
- 3 Claude Opus 4.5 8.60%
- 4
Gemini 2.5 Flash Jun 2025 7.30%
- 5
Llama 4 Maverick 6.50%
- 6 GPT-5 mini 6.40%
Source: Official AI GameStore leaderboard
| # | Entry | Score ± 95% CI | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 12.4% 4.8 to 18.1 | Jun 2025 | Official leaderboard | |
| 2 | GPT-5.2 | 10.7% 5.6 to 17.1 | Dec 2025 | Official leaderboard | |
| 3 | Claude Opus 4.5 | 8.60% 4 to 17.9 | Nov 2025 | Official leaderboard | |
| 4 | | 7.30% 4 to 13.7 | Jun 2025 | Official leaderboard | |
| 5 | | 6.50% 3.9 to 11.3 | Apr 2025 | Official leaderboard | |
| 6 | GPT-5 mini | 6.40% 2 to 15 | Aug 2025 | Official leaderboard | |
| 7 | Qwen3-VL-32B | 3.50% 0 to 7.4 | Official leaderboard |
| # | Model | Score ± 95% CI | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 12.4% 4.8 to 18.1 | Jun 2025 | Official leaderboard | |
| 2 | GPT-5.2 | 10.7% 5.6 to 17.1 | Dec 2025 | Official leaderboard | |
| 3 | Claude Opus 4.5 | 8.60% 4 to 17.9 | Nov 2025 | Official leaderboard | |
| 4 | | 7.30% 4 to 13.7 | Jun 2025 | Official leaderboard | |
| 5 | | 6.50% 3.9 to 11.3 | Apr 2025 | Official leaderboard | |
| 6 | GPT-5 mini | 6.40% 2 to 15 | Aug 2025 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: Public games and Private games. Each ranks models on one part of the test. Gemini 2.5 Pro leads both. Arrows show how far a model moved from its overall rank among the models we track.
Public games
The 10 games anyone can play on the site. 6 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 15.1%
- 2
Gemini 2.5 Flash Jun 2025 ↑2 11.2%
- 3 GPT-5.2 ↓1 5.90%
- 4 Claude Opus 4.5 ↓1 5.40%
- 5
Llama 4 Maverick 3.50%
- 6 GPT-5 mini 3.10%
Private games
The 90 games kept off the site. 6 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 11.7%
- 2 GPT-5.2 11.1%
- 3 Claude Opus 4.5 9.10%
- 4
Gemini 2.5 Flash Jun 2025 7.30%
- 5
Llama 4 Maverick 7.00%
- 6 GPT-5 mini 6.40%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official AI GameStore leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official AI GameStore leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Games and long tasks
- ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6.2 Astra 100%
- Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Each game scores in-game progress or outcomes, and the board ranks models by their average rank across the games.
Gemini 2.5 Pro 3.90
- MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks.
Seed2.0 Pro 49%
- TextQuests Only in system cards Agents play 25 classic interactive fiction games. The score is harmful actions per 100 steps, where lower is better. The board also reports game progress.
Llama 4 Scout 7.00
- GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. GPT-6.1 Terra 76.8%
- Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 11 months ago, in December 2025, for GPT-5.2. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (7 entries).
- Pass Models scored 6 models we track, plus 1 other entry on its leaderboard.
- Warning Newest score The newest came 11 months ago, in December 2025, for GPT-5.2.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.2 (#51).
- Pass Headroom The best is 12.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on aigamestore.org: 6 rows for models we track and 1 other entry at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.