AAArena
Agents write and revise programs for 12 games. Each program competes against archived human entries under a fixed match budget.
The October 2026 paper reports six gold medals for Claude Opus 5.5 with Claude Code, the most of any configuration.
- Made by
- AAArena team
- Released
- October 2026
- Kind
- Multi-agent games
- Level
- University
- Scored
- Ranked by matches
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Code sandbox
- Items from
- Real work and use, Live play or votes
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents
- Strongest model tested
- Claude Opus 5.5 #5 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 6.00 among models released by September 2026 Claude Opus 5.5 leads with 6.00 among models released by September 2026
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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 September 2026, 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-6.1 Sol
- and 14 more
- 1 Claude Opus 5.5 Max reasoning, 128 small and 16 full evaluations 6.00
- 2 GLM-5.3 Max reasoning, 128 small and 16 full evaluations 4.00
- 3 GPT-6 Sol Max reasoning, 128 small and 16 full evaluations 4.00
- 4 Qwen 3.8 Max reasoning, 128 small and 16 full evaluations 3.00
- 5
DeepSeek-V4-Pro Max reasoning, 128 small and 16 full evaluations 2.00
- 6 Kimi K3 Max reasoning, 128 small and 16 full evaluations 2.00
- 7
LongCat-2.0 Max reasoning, 128 small and 16 full evaluations 1.00
Source: The AAArena paper
- 1 Claude Opus 5.5 Max reasoning, 128 small and 16 full evaluations 6.00
- 2 GLM-5.3 Max reasoning, 128 small and 16 full evaluations 4.00
- 3 GPT-6 Sol Max reasoning, 128 small and 16 full evaluations 4.00
- 4
DeepSeek-V4-Pro Max reasoning, 128 small and 16 full evaluations 2.00
- 5 Kimi K3 Max reasoning, 128 small and 16 full evaluations 2.00
- 6
LongCat-2.0 Max reasoning, 128 small and 16 full evaluations 1.00
Source: The AAArena paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 6.00 | Max reasoning, 128 small and 16 full evaluations, Claude Code | Sep 2026 | Official leaderboard |
| 2 | GLM-5.3 | 4.00 | Max reasoning, 128 small and 16 full evaluations, Codex | Aug 2026 | Official leaderboard |
| 3 | GPT-6 Sol | 4.00 | Max reasoning, 128 small and 16 full evaluations, Codex | Sep 2026 | Official leaderboard |
| 4 | Qwen 3.8 | 3.00 | Max reasoning, 128 small and 16 full evaluations, Codex | Official leaderboard | |
| 5 | | 2.00 | Max reasoning, 128 small and 16 full evaluations, Codex | Apr 2026 | Official leaderboard |
| 6 | Kimi K3 | 2.00 | Max reasoning, 128 small and 16 full evaluations, Codex | Jul 2026 | Official leaderboard |
| 7 | | 1.00 | Max reasoning, 128 small and 16 full evaluations, Codex | Jul 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 6.00 | Max reasoning, 128 small and 16 full evaluations, Claude Code | Sep 2026 | Official leaderboard |
| 2 | GLM-5.3 | 4.00 | Max reasoning, 128 small and 16 full evaluations, Codex | Aug 2026 | Official leaderboard |
| 3 | GPT-6 Sol | 4.00 | Max reasoning, 128 small and 16 full evaluations, Codex | Sep 2026 | Official leaderboard |
| 4 | | 2.00 | Max reasoning, 128 small and 16 full evaluations, Codex | Apr 2026 | Official leaderboard |
| 5 | Kimi K3 | 2.00 | Max reasoning, 128 small and 16 full evaluations, Codex | Jul 2026 | Official leaderboard |
| 6 | | 1.00 | Max reasoning, 128 small and 16 full evaluations, Codex | Jul 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The AAArena paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official AAArena 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
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (7 entries).
- Pass Models scored 6 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from September 2026, for Claude Opus 5.5.
- Note Frontier models Only 1 of the top 10 has a score. The strongest tested is Claude Opus 5.5 (#5).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.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.