CG-AL-X292
Description
Per-model results
| Model | Attempt 1 | Attempt 2 | Avg score | Tokens / attempt | Runs |
|---|---|---|---|---|---|
| Claude Opus 5.5 | ✓ | — | 100.0 / 100 | 8.3k / 3.9k | 3 |
| GPT-6.1 Sol | ✓ | — | 100.0 / 100 | 4.8k / 1.7k | 3 |
| Claude Opus 5 | ✓ | ✓ | 85.0 / 100 | 9.1k / 10.0k | 3 |
| GPT-5.6 Sol | ✓ | ✓ | 85.0 / 100 | 5.3k / 2.6k | 3 |
| GPT-5.6 Terra | ✗ | ✓ | 81.3 / 100 | 7.1k / 2.0k | 3 |
| GPT-6 Luna | ✗ | ✓ | 81.3 / 100 | 5.7k / 2.3k | 3 |
| MiniMax M3 | ✗ | ✓ | 81.3 / 100 | 6.1k / 13k | 3 |
| GPT-6 Sol | ✓ | ✓ | 65.0 / 100 | 4.9k / 1.7k | 3 |
| Claude Sonnet 5 | ✗ | ✓ | 64.6 / 100 | 10k / 15k | 3 |
| GPT-5.6 Luna | ✗ | ✓ | 64.6 / 100 | 6.4k / 1.7k | 3 |
| Claude Haiku 4 5 | ✗ | ✗ | 62.5 / 100 | 10k / 1.4k | 3 |
| Gemini 3.8 Flash (OpenRouter) | ✗ | ✓ | 47.9 / 100 | 6.5k / 31k | 3 |
| GLM 5.3 (OpenRouter) | ✗ | ✓ | 40.6 / 100 | 5.1k / 60k | 2 |