CG-AL-X214
Description
Per-model results
| Model | Attempt 1 | Attempt 2 | Avg score | Tokens / attempt | Runs |
|---|---|---|---|---|---|
| Claude Opus 5.5 | ✗ | ✓ | 81.3 / 100 | 6.7k / 3.4k | 3 |
| Claude Sonnet 5 | ✗ | ✓ | 81.3 / 100 | 6.9k / 7.4k | 3 |
| GPT-5.6 Sol | ✗ | ✓ | 81.3 / 100 | 4.0k / 2.9k | 3 |
| GPT-5.6 Terra | ✗ | ✓ | 81.3 / 100 | 4.0k / 2.1k | 3 |
| Claude Opus 5 | ✗ | ✓ | 75.0 / 100 | 6.7k / 11k | 3 |
| GPT-6 Sol | ✗ | ✓ | 75.0 / 100 | 4.0k / 2.3k | 3 |
| GPT-6 Luna | ✗ | ✓ | 68.8 / 100 | 5.0k / 3.3k | 3 |
| Gemini 3.8 Flash (OpenRouter) | ✗ | ✓ | 68.8 / 100 | 4.6k / 30k | 3 |
| GPT-5.6 Luna | ✗ | ✓ | 64.6 / 100 | 4.3k / 2.9k | 3 |
| Claude Haiku 4 5 | ✗ | ✗ | 62.5 / 100 | 5.3k / 1.4k | 3 |
| GPT-6.1 Sol | ✗ | ✗ | 62.5 / 100 | 3.9k / 1.3k | 3 |
| MiniMax M3 | ✗ | ✗ | 62.5 / 100 | 4.3k / 14k | 3 |
| GLM 5.3 (OpenRouter) | ✗ | ✗ | 31.3 / 100 | 4.2k / 47k | 2 |