CG-AL-X211
Description
Per-model results
| Model | Attempt 1 | Attempt 2 | Avg score | Tokens / attempt | Runs |
|---|---|---|---|---|---|
| Claude Opus 5.5 | ✓ | — | 100.0 / 100 | 6.0k / 5.1k | 3 |
| Claude Opus 5 | ✓ | ✓ | 85.0 / 100 | 6.7k / 15k | 3 |
| GPT-6.1 Sol | ✓ | ✓ | 85.0 / 100 | 3.8k / 2.1k | 3 |
| GPT-5.6 Sol | ✗ | ✓ | 81.3 / 100 | 4.6k / 3.6k | 3 |
| GPT-5.6 Luna | ✗ | ✓ | 75.0 / 100 | 4.8k / 2.7k | 3 |
| Gemini 3.8 Flash (OpenRouter) | ✗ | ✓ | 75.0 / 100 | 4.7k / 19k | 3 |
| GPT-6 Sol | ✓ | ✓ | 65.0 / 100 | 4.0k / 2.4k | 3 |
| GPT-5.6 Terra | ✗ | ✓ | 64.6 / 100 | 4.4k / 2.9k | 3 |
| MiniMax M3 | ✗ | ✓ | 58.3 / 100 | 5.1k / 23k | 3 |
| Claude Haiku 4 5 | ✗ | ✗ | 52.1 / 100 | 5.9k / 2.3k | 3 |
| Claude Sonnet 5 | ✗ | ✓ | 47.9 / 100 | 7.0k / 8.4k | 3 |
| GPT-6 Luna | ✗ | ✓ | 47.9 / 100 | 4.2k / 3.2k | 3 |
| GLM 5.3 (OpenRouter) | ✗ | ✗ | 0.0 / 100 | 3.0k / 64k | 2 |