CG-AL-X245
Description
Per-model results
| Model | Attempt 1 | Attempt 2 | Avg score | Tokens / attempt | Runs |
|---|---|---|---|---|---|
| GPT-6.1 Sol | ✓ | — | 100.0 / 100 | 4.3k / 2.1k | 3 |
| Gemini 3.8 Flash (OpenRouter) | ✓ | — | 100.0 / 100 | 5.0k / 30k | 3 |
| Claude Opus 5.5 | ✓ | ✓ | 85.0 / 100 | 8.3k / 2.7k | 3 |
| GPT-6 Sol | ✓ | ✓ | 85.0 / 100 | 4.8k / 1.7k | 3 |
| Claude Opus 5 | ✗ | ✓ | 81.3 / 100 | 8.9k / 5.9k | 3 |
| Claude Sonnet 5 | ✗ | ✓ | 81.3 / 100 | 9.9k / 9.0k | 3 |
| GPT-5.6 Sol | ✗ | ✓ | 81.3 / 100 | 5.0k / 2.0k | 3 |
| GPT-5.6 Terra | ✗ | ✓ | 81.3 / 100 | 5.1k / 2.3k | 3 |
| GPT-5.6 Luna | ✗ | ✓ | 68.8 / 100 | 6.9k / 3.3k | 3 |
| Claude Haiku 4 5 | ✗ | ✗ | 62.5 / 100 | 9.5k / 1.1k | 3 |
| GPT-6 Luna | ✗ | ✓ | 58.3 / 100 | 5.6k / 2.3k | 3 |
| GLM 5.3 (OpenRouter) | ✗ | ✓ | 56.3 / 100 | 6.0k / 47k | 2 |
| MiniMax M3 | ✗ | ✗ | 52.1 / 100 | 5.4k / 12k | 3 |