CG-AL-X185
Summary
Exact model prompt
Per-model results
| Model | Attempt 1 | Attempt 2 | Avg score | Tokens / attempt | Runs |
|---|---|---|---|---|---|
| GPT-6 Luna | ✗ | ✓ | 75.0 / 100 | 3.4k / 2.0k | 3 |
| GPT-6.1 Sol | ✗ | ✓ | 75.0 / 100 | 2.7k / 812 | 3 |
| Claude Sonnet 5 | ✗ | ✓ | 68.8 / 100 | 5.9k / 4.3k | 3 |
| Claude Opus 5 | ✗ | ✗ | 62.5 / 100 | 5.9k / 3.9k | 3 |
| Claude Opus 5.5 | ✗ | ✗ | 62.5 / 100 | 4.6k / 1.6k | 3 |
| GPT-5.6 Luna | ✗ | ✗ | 62.5 / 100 | 3.4k / 1.6k | 3 |
| GPT-5.6 Sol | ✗ | ✗ | 62.5 / 100 | 3.2k / 1.5k | 3 |
| GPT-5.6 Terra | ✗ | ✗ | 62.5 / 100 | 3.4k / 1.8k | 3 |
| GPT-6 Sol | ✗ | ✗ | 62.5 / 100 | 3.2k / 909 | 3 |
| Gemini 3.8 Flash (OpenRouter) | ✗ | ✗ | 62.5 / 100 | 3.1k / 8.7k | 3 |
| GLM 5.3 (OpenRouter) | ✗ | ✓ | 56.3 / 100 | 3.5k / 49k | 2 |
| Claude Haiku 4 5 | ✗ | ✗ | 52.1 / 100 | 5.0k / 810 | 3 |
| MiniMax M3 | ✗ | ✓ | 47.9 / 100 | 3.7k / 5.8k | 3 |