# TencentARC/GameHorizon

> Official repo of GameHorizon, a data and evaluation suite for measuring model gameplay capabilities in AAA games across different temporal horizons, with 5,000 hours of gameplay and offline/online benchmarks.

- Magnitude: 4.5 out of 10 — Early signal
- Stars: 123 total · +73 stars today, ≈ 108 by evening
- Star trust: star growth looks organic
- Category: Language models · License: Apache-2.0 · Created: 2026-09-20 · Last push: 2026-09-22
- GitHub: https://github.com/TencentARC/GameHorizon · Page: https://gitnova.dev/en/r/TencentARC/GameHorizon

## Useful for

- Evaluate your VLM on the GameHorizon-Bench offline MCQ suite
- Compare models by success rate on online short- and long-horizon tasks
- Use the 5,000-hour gameplay corpus to train or fine-tune a model

## Why it’s here

- 73 stars so far today, about 108 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 2 days old and already has 123 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #166.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1
- Issues and pull requests: 0
- Watchers: 4
- Average over the last week: 53 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 11

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-09-20 … 2026-09-22: 1, 51, 73

## Spotted in now

- Top new repositories this week: #166

## More in this category

1. **jaredpalmer/kev** — 8.9 · Breakout · Language models · Python · +635 stars today, ≈ 1,092 by evening
   kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.
   Full card: https://gitnova.dev/en/r/jaredpalmer/kev.md
2. **mizorewww/laya-mlx** — 8.7 · Breakout · Language models · Python · +678 stars today, ≈ 1,270 by evening
   Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.
   Full card: https://gitnova.dev/en/r/mizorewww/laya-mlx.md
3. **volotat/mini-AGI** — 7.4 · Early signal · Language models · Python · +153 stars today, ≈ 259 by evening
   A byte-level continual-learning language model that assembles its own architecture, trains from scratch on a single 8 GB VRAM GPU, and keeps learning from everything it reads. An experiment showing continual learning without catastrophic…
   Full card: https://gitnova.dev/en/r/volotat/mini-AGI.md
4. **TheoLeeCJ/SemIf** — 7.2 · Peaking · Language models · Python · +246 stars today, ≈ 454 by evening
   An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.
   Full card: https://gitnova.dev/en/r/TheoLeeCJ/SemIf.md
5. **mizorewww/laya-coreml** — 6.8 · Early signal · Language models · Python · +149 stars today, ≈ 280 by evening
   Local port of the Laya model to Apple Core ML and Neural Engine: returns typed decisions (choice, score, yes/no) without token generation, with speed and energy benchmarks.
   Full card: https://gitnova.dev/en/r/mizorewww/laya-coreml.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-22 14:52 UTC, updated every 30 minutes.