gg-bench
Models play 126 games invented by a language model and receive game-specific outcomes.
The May 2025 paper compares models across 126 generated games. The abstract does not state the best score.
- Made by
- gg-bench authors
- Released
- May 2025
- Kind
- Puzzles and chess
- Level
- Everyday
- Scored
- Settled by events
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Multi-agent
- Environment
- A simulator
- Items from
- Generated
- Refresh
- Live
- Run by
- Anyone
- In views
- Agents, Robotics, Kept fresh
- Strongest model tested
- o1 #118 on the capability index
- Last model added
- February 2025
- Scores refreshed
- November 20th, 2026
o1 leads with 36.3% among models released by February 2025 o1 leads with 36.3% among models released by February 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 February 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 o1 36.3%
- 2 deepseek-r1 (snapshot unspecified) 32.5%
- 3 o3-mini 31.1%
- 4 Claude 3.7 Sonnet 9.53%
- 5 gpt-4o (snapshot unspecified) 8.94%
- 6 gpt-4o-mini (snapshot unspecified) 7.64%
- 7
Llama 3.3 70B 7.42%
Source: Official gg-bench leaderboard
- 1 o1 36.3%
- 2 o3-mini 31.1%
- 3 Claude 3.7 Sonnet 9.53%
- 4
Llama 3.3 70B 7.42%
Source: Official gg-bench leaderboard
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1 | 36.3% ±5.9 | Dec 2024 | Official leaderboard | |
| 2 | deepseek-r1 (snapshot unspecified) | 32.5% ±5.1 | Official leaderboard | ||
| 3 | o3-mini | 31.1% ±5.7 | Jan 2025 | Official leaderboard | |
| 4 | Claude 3.7 Sonnet | 9.53% ±3.1 | Feb 2025 | Official leaderboard | |
| 5 | gpt-4o (snapshot unspecified) | 8.94% ±2.8 | Official leaderboard | ||
| 6 | gpt-4o-mini (snapshot unspecified) | 7.64% ±2.3 | Official leaderboard | ||
| 7 | | 7.42% ±2.8 | Dec 2024 | Official leaderboard |
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1 | 36.3% ±5.9 | Dec 2024 | Official leaderboard | |
| 2 | o3-mini | 31.1% ±5.7 | Jan 2025 | Official leaderboard | |
| 3 | Claude 3.7 Sonnet | 9.53% ±3.1 | Feb 2025 | Official leaderboard | |
| 4 | | 7.42% ±2.8 | Dec 2024 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official gg-bench 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 gg-bench 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 21 months ago, in February 2025, for Claude 3.7 Sonnet. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- 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 4 models we track, plus 3 other entries on its leaderboard.
- Warning Newest score The newest came 21 months ago, in February 2025, for Claude 3.7 Sonnet.
- Note Frontier models None of the top 10 has a score. The strongest tested is o1 (#118).
- Pass Headroom The best is 36.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 4 rows for models we track and 3 other entries 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.