CG-AL-X296
Description
Per-model results
| Model | Attempt 1 | Attempt 2 | Avg score | Tokens / attempt | Runs |
|---|---|---|---|---|---|
| GPT-6.1 Sol | ✓ | — | 100.0 / 100 | 6.6k / 4.6k | 3 |
| GPT-5.6 Sol | ✓ | ✓ | 90.6 / 100 | 8.2k / 6.6k | 3 |
| Claude Opus 5 | ✗ | ✓ | 81.3 / 100 | 13k / 14k | 3 |
| Claude Opus 5.5 | ✗ | ✓ | 81.3 / 100 | 12k / 6.9k | 3 |
| GPT-6 Luna | ✗ | ✓ | 81.3 / 100 | 8.5k / 5.0k | 3 |
| GPT-6 Sol | ✗ | ✓ | 81.3 / 100 | 7.0k / 3.8k | 3 |
| Gemini 3.8 Flash (OpenRouter) | ✗ | ✓ | 81.3 / 100 | 8.0k / 28k | 3 |
| Claude Haiku 4 5 | ✗ | ✗ | 62.5 / 100 | 10k / 3.0k | 3 |
| Claude Sonnet 5 | ✗ | ✗ | 62.5 / 100 | 15k / 13k | 3 |
| GPT-5.6 Luna | ✗ | ✗ | 62.5 / 100 | 8.4k / 3.8k | 3 |
| MiniMax M3 | ✗ | ✗ | 62.5 / 100 | 8.7k / 23k | 3 |
| GPT-5.6 Terra | ✗ | ✗ | 41.7 / 100 | 7.7k / 4.8k | 3 |
| GLM 5.3 (OpenRouter) | ✗ | ✗ | 31.3 / 100 | 8.1k / 53k | 2 |