CG-AL-X244
Description
Per-model results
| Model | Attempt 1 | Attempt 2 | Avg score | Tokens / attempt | Runs |
|---|---|---|---|---|---|
| Claude Opus 5.5 | ✗ | ✓ | 81.3 / 100 | 10k / 5.3k | 3 |
| Claude Opus 5 | ✗ | ✓ | 75.0 / 100 | 10k / 18k | 3 |
| Claude Sonnet 5 | ✗ | ✓ | 75.0 / 100 | 9.9k / 13k | 3 |
| GPT-5.6 Sol | ✗ | ✓ | 75.0 / 100 | 5.6k / 3.7k | 3 |
| GPT-5.6 Terra | ✗ | ✓ | 75.0 / 100 | 5.6k / 3.7k | 3 |
| GPT-6 Sol | ✗ | ✓ | 75.0 / 100 | 5.7k / 3.0k | 3 |
| Claude Haiku 4 5 | ✗ | ✓ | 68.8 / 100 | 7.6k / 2.1k | 3 |
| GPT-6 Luna | ✗ | ✓ | 68.8 / 100 | 5.9k / 5.2k | 3 |
| GPT-6.1 Sol | ✗ | ✓ | 68.8 / 100 | 5.7k / 2.8k | 3 |
| Gemini 3.8 Flash (OpenRouter) | ✗ | ✓ | 68.8 / 100 | 6.7k / 41k | 3 |
| MiniMax M3 | ✗ | ✓ | 68.8 / 100 | 6.7k / 20k | 3 |
| GPT-5.6 Luna | ✗ | ✓ | 47.9 / 100 | 5.4k / 3.3k | 3 |
| GLM 5.3 (OpenRouter) | ✗ | ✗ | 15.6 / 100 | 4.4k / 61k | 2 |