CG-AL-X274
Description
Per-model results
| Model | Attempt 1 | Attempt 2 | Avg score | Tokens / attempt | Runs |
|---|---|---|---|---|---|
| GPT-5.6 Sol | ✗ | ✓ | 81.3 / 100 | 6.5k / 3.8k | 3 |
| GPT-5.6 Terra | ✗ | ✓ | 81.3 / 100 | 6.8k / 3.5k | 3 |
| GPT-6.1 Sol | ✗ | ✓ | 81.3 / 100 | 6.0k / 2.8k | 3 |
| Gemini 3.8 Flash (OpenRouter) | ✗ | ✓ | 81.3 / 100 | 7.1k / 25k | 3 |
| Claude Opus 5 | ✗ | ✓ | 75.0 / 100 | 12k / 11k | 3 |
| Claude Sonnet 5 | ✗ | ✓ | 75.0 / 100 | 12k / 12k | 3 |
| GPT-6 Sol | ✗ | ✓ | 75.0 / 100 | 6.4k / 2.8k | 3 |
| Claude Opus 5.5 | ✗ | ✓ | 68.8 / 100 | 11k / 5.7k | 3 |
| Claude Haiku 4 5 | ✗ | ✗ | 62.5 / 100 | 9.7k / 3.8k | 3 |
| GPT-5.6 Luna | ✗ | ✓ | 58.3 / 100 | 8.4k / 3.2k | 3 |
| GPT-6 Luna | ✗ | ✓ | 47.9 / 100 | 7.7k / 4.2k | 3 |
| MiniMax M3 | ✗ | ✗ | 20.8 / 100 | 3.6k / 13k | 3 |
| GLM 5.3 (OpenRouter) | ✗ | ✗ | 15.6 / 100 | 5.3k / 59k | 2 |