multimodal benchmark
GameWorld Leaderboard
GameWorld evaluates agents in interactive game environments on their ability to accomplish in-game objectives.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
GameWorld Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelBY | Score31.20% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelBY | Score25.90% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
GameWorld Highlights
The leading models and scores on this benchmark.
GameWorld Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for GameWorld
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is GameWorld?
What GameWorld measures and how its scores work.
GameWorld is a multimodal benchmark for evaluating agents in interactive game environments.
It measures perception, planning, and sequential decision-making for accomplishing in-game objectives using Score, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- GameWorld
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about GameWorld.
Which model scores highest on GameWorld?
Seed 2.1 Pro is currently ranked first with 31.20%.
What are the top three models on GameWorld?
The current leaders are Seed 2.1 Pro (31.20%) and Seed 2.1 Turbo (25.90%).
Which GameWorld model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among GameWorld results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.