SpaceChem Bench: Ω-Pseudoethyne
Random inputs: α Carbomega (Ω / C), β Hydrogen (H2). Output: ψ Ω-Pseudoethyne (ΩH3CH) ×40. Features: Max reactors: 2, Random inputs.
In SpaceChem Bench, 16 LLMs each had one attempt at this SpaceChem puzzle, with 60 minutes to build a working solution and keep optimizing it, without seeing the community archive. 0 of 16 models solved it. No model found a new Pareto-frontier point beyond the frozen community archive.
Records
| Score | Community best | Best LLM | Model |
|---|---|---|---|
| Cycles | 839 | No model solved it | |
| Reactors | 2 | No model solved it | |
| Symbols | 41 | No model solved it | |
Community records from the community archive when we froze it on October 18, 2026. A point counts only after fresh-game replay and SChem’s precognition check.
Pareto frontier
Pareto explorer
Lower is better ↙Search over time
Loading puzzle trajectories…
The search over time
Best in-game score so far, before replay. Each score can come from a different solution, and lines stop when the episode ends.
Every model
| Model | Solved | Best cycles | Best reactors | Best symbols | New frontier points |
|---|---|---|---|---|---|
| 01DeepSeek V4.1 Flash | No | — | — | — | — |
| 02Fable 5.1 | No | — | — | — | — |
| 03GLM-5.3 | No | — | — | — | — |
| 04GPT-6 Astra | No | — | — | — | — |
| 05GPT-6 Luna | No | — | — | — | — |
| 06GPT-6.1 Sol | No | — | — | — | — |
| 07Gemini 3.8 Flash | No | — | — | — | — |
| 08Gemini 4 Argon | No | — | — | — | — |
| 09Grok 4.7 | No | — | — | — | — |
| 10Haiku 5.5 | No | — | — | — | — |
| 11Kimi K3.1 Pro | No | — | — | — | — |
| 12MiMo-V2.6-Pro | No | — | — | — | — |
| 13Muse Spark 1.3 | No | — | — | — | — |
| 14Muse Wonder 1.0 | No | — | — | — | — |
| 15Opus 5.5 | No | — | — | — | — |
| 16Sonnet 5.5 | No | — | — | — | — |
Best scores can come from different solutions. New frontier points are not matched or beaten on all three scores by any community solution.
Best model solutions
No model solved this puzzle.