MOLTRON LLM Showdown v2.0
Version 2.0
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 a local map and can query occupied cells. The maker’s leaderboard reports six models, with up to ten bots per model.
- 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
- Items from
- Generated
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- MOLTRON LLM Showdown v1.0
- Strongest model tested
- Claude Opus 4.8 #22 on the capability index
- Last model added
- May 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 4.8 leads with 55.7% among models released by May 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 May 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 Astra
- and 16 more
- 1 Claude Opus 4.8 55.7%
- 2 GPT-5 46%
- 3
Gemini 3.1 Flash-Lite 32%
- 4 GPT-4o Mar 2025 17.4%
- 5
Gemini 3.1 Pro 11.6%
- 6
Gemini 3.5 Flash 6.97%
Source: Official MOLTRON LLM Showdown v2.0 leaderboard
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | 55.7% ±11.7 | May 2026 | Official leaderboard | |
| 2 | GPT-5 | 46% ±13.7 | Aug 2025 | Official leaderboard | |
| 3 | | 32% ±12.5 | Mar 2026 | Official leaderboard | |
| 4 | GPT-4o Mar 2025 | 17.4% ±15.8 | Mar 2025 | Official leaderboard | |
| 5 | | 11.6% ±9.3 | Feb 2026 | Official leaderboard | |
| 6 | | 6.97% ±2.6 | 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. Claude Opus 4.8 leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
vs hunter
6 models we track have a score here.
- 1 Claude Opus 4.8 71%
- 2 GPT-5 65%
- 3
Gemini 3.1 Flash-Lite 47%
- 4 GPT-4o Mar 2025 28%
- 5
Gemini 3.1 Pro 24%
- 6
Gemini 3.5 Flash 17%
vs hoarder
6 models we track have a score here.
- 1 Claude Opus 4.8 63%
- 2 GPT-5 60%
- 3
Gemini 3.1 Flash-Lite 43%
- 4 GPT-4o Mar 2025 22%
- 5
Gemini 3.1 Pro 18%
- 6
Gemini 3.5 Flash 11%
vs survivor
6 models we track have a score here.
- 1 Claude Opus 4.8 48%
- 2 GPT-5 35%
- 3
Gemini 3.1 Flash-Lite 24%
- 4 GPT-4o Mar 2025 11%
- 5
Gemini 3.1 Pro 4.00%
- 6
Gemini 3.5 Flash 0%
vs seeker
6 models we track have a score here.
- 1 Claude Opus 4.8 51%
- 2 GPT-5 36%
- 3
Gemini 3.1 Flash-Lite 22%
- 4 GPT-4o Mar 2025 12%
- 5
Gemini 3.1 Pro 6.00%
- 6
Gemini 3.5 Flash 2.00%
vs collector
6 models we track have a score here.
- 1 Claude Opus 4.8 46%
- 2 GPT-5 34%
- 3
Gemini 3.1 Flash-Lite 24%
- 4 GPT-4o Mar 2025 14%
- 5
Gemini 3.1 Pro 6.00%
- 6
Gemini 3.5 Flash 4.00%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official MOLTRON LLM Showdown v2.0 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 v2.0 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 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 official leaderboard (6 entries).
- Pass Models scored 6 models we track.
- Note Newest score The newest came 6 months ago, in May 2026, for Claude Opus 4.8. That’s expected for a test replaced by MOLTRON LLM Showdown v3.0.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Opus 4.8 (#22).
- Pass Headroom The best is 55.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on ageofmoltron.com: 6 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.