MOLTRON LLM Showdown v3.0
Version 3.0
Models write JavaScript bots for a light-cycle game. Each working bot plays 600 matches against five reference opponents across six maps and both starting positions.
Bots receive ownership and hazard information as well as the local map. The maker’s leaderboard reports eleven models and 62,400 matches.
- Made by
- MOLTRON
- Released
- September 2026
- Kind
- Video games
- Level
- University
- Scored
- Settled by events
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Environment
- Tron
- Items from
- Generated
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- MOLTRON LLM Showdown v1.0
- In views
- Games
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
GPT-6 Astra leads with 69% among models released by September 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep 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 GPT-6 Astra 69%
- 2 Claude Opus 4.8 59.7%
- 3
Gemini 3.8 Flash 56.8%
- 4 Claude Opus 5.5 53.2%
- 5 GPT-6 Luna 42.7%
- 6 GPT-5 40.6%
- 7 GPT-4o Mar 2025 28.2%
- 8 Claude Haiku 4.5 27.1%
- 9
Gemini 3.1 Flash-Lite 23.5%
- 10
Gemini 3.1 Pro 17.9%
- 11
Gemini 3.5 Flash 8.75%
Source: Official MOLTRON LLM Showdown v3.0 leaderboard
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 69% ±3.6 | Sep 2026 | Official leaderboard | |
| 2 | Claude Opus 4.8 | 59.7% ±9 | May 2026 | Official leaderboard | |
| 3 | | 56.8% ±11.9 | Sep 2026 | Official leaderboard | |
| 4 | Claude Opus 5.5 | 53.2% ±13.2 | Sep 2026 | Official leaderboard | |
| 5 | GPT-6 Luna | 42.7% ±16.9 | Sep 2026 | Official leaderboard | |
| 6 | GPT-5 | 40.6% ±15.9 | Aug 2025 | Official leaderboard | |
| 7 | GPT-4o Mar 2025 | 28.2% ±16.6 | Mar 2025 | Official leaderboard | |
| 8 | Claude Haiku 4.5 | 27.1% ±14.3 | Oct 2025 | Official leaderboard | |
| 9 | | 23.5% ±20.9 | Mar 2026 | Official leaderboard | |
| 10 | | 17.9% ±14.2 | Feb 2026 | Official leaderboard | |
| 11 | | 8.75% ±8.2 | May 2026 | Official leaderboard |
Rankings by part
We read 5 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as vs hunter, vs hoarder and vs survivor. GPT-6 Astra leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
vs hunter
11 models we track have a score here.
- 1 GPT-6 Astra 90%
- 2 Claude Opus 4.8 76%
- 3
Gemini 3.8 Flash 72%
- 4 Claude Opus 5.5 67%
- 5 GPT-5 ↑1 62%
- 6 GPT-6 Luna ↓1 59%
- 7 GPT-4o Mar 2025 44%
- 8 Claude Haiku 4.5 43%
- 9
Gemini 3.1 Flash-Lite 38%
- 10
Gemini 3.1 Pro 31%
vs hoarder
11 models we track have a score here.
- 1 GPT-6 Astra 79%
- 2 Claude Opus 4.8 69%
- 3
Gemini 3.8 Flash 63%
- 4 Claude Opus 5.5 60%
- 5 GPT-6 Luna 54%
- 6 GPT-5 52%
- 7 Claude Haiku 4.5 ↑1 38%
- 8 GPT-4o Mar 2025 ↓1 35%
- 9
Gemini 3.1 Flash-Lite 32%
- 10
Gemini 3.1 Pro 25%
vs survivor
11 models we track have a score here.
- 1 GPT-6 Astra 58%
- 2 Claude Opus 4.8 52%
- 3
Gemini 3.8 Flash 51%
- 4 Claude Opus 5.5 47%
- 5 GPT-6 Luna 35%
- 6 GPT-5 29%
- 7 GPT-4o Mar 2025 19%
- 8 Claude Haiku 4.5 16%
- 9
Gemini 3.1 Flash-Lite 15%
- 10
Gemini 3.1 Pro 10%
vs seeker
11 models we track have a score here.
- 1 GPT-6 Astra 65%
- 2 Claude Opus 4.8 55%
- 3
Gemini 3.8 Flash 53%
- 4 Claude Opus 5.5 52%
- 5 GPT-6 Luna 35%
- 6 GPT-5 31%
- 7 GPT-4o Mar 2025 20%
- 8 Claude Haiku 4.5 18%
- 9
Gemini 3.1 Flash-Lite 15%
- 10
Gemini 3.1 Pro 11%
vs collector
11 models we track have a score here.
- 1 GPT-6 Astra 53%
- 2 Claude Opus 4.8 47%
- 3
Gemini 3.8 Flash 45%
- 4 Claude Opus 5.5 40%
- 5 GPT-6 Luna 31%
- 6 GPT-5 30%
- 7 GPT-4o Mar 2025 22%
- 8 Claude Haiku 4.5 21%
- 9
Gemini 3.1 Flash-Lite 18%
- 10
Gemini 3.1 Pro 13%
2 models have held number one on the official leaderboard since its release in September 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official MOLTRON LLM Showdown v3.0 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 MOLTRON LLM Showdown v3.0 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.
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Source: Official leaderboards
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 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (11 entries).
- Pass Models scored 11 models we track.
- Pass Newest score The newest is from September 2026, for Claude Opus 5.5.
- Note Frontier models Only 2 of the top 10 have a score. The strongest tested is GPT-6 Astra (#4).
- Pass Headroom The best is 69%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on ageofmoltron.com: 11 rows for models we track 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.