CG-AL-X293
Description
Per-model results
| Model | Attempt 1 | Attempt 2 | Avg score | Tokens / attempt | Runs |
|---|---|---|---|---|---|
| Claude Opus 5.5 | ✓ | — | 100.0 / 100 | 7.5k / 5.2k | 3 |
| GPT-6.1 Sol | ✓ | — | 100.0 / 100 | 4.3k / 2.8k | 3 |
| Gemini 3.8 Flash (OpenRouter) | ✓ | — | 100.0 / 100 | 5.0k / 39k | 3 |
| Claude Opus 5 | ✗ | ✓ | 81.3 / 100 | 8.9k / 6.6k | 3 |
| Claude Sonnet 5 | ✗ | ✓ | 81.3 / 100 | 8.8k / 9.4k | 3 |
| GPT-5.6 Luna | ✗ | ✓ | 81.3 / 100 | 5.4k / 2.5k | 3 |
| GPT-5.6 Sol | ✗ | ✓ | 81.3 / 100 | 5.1k / 2.8k | 3 |
| GPT-5.6 Terra | ✗ | ✓ | 81.3 / 100 | 5.1k / 2.2k | 3 |
| GPT-6 Luna | ✗ | ✓ | 81.3 / 100 | 5.1k / 2.5k | 3 |
| GPT-6 Sol | ✗ | ✓ | 81.3 / 100 | 5.1k / 1.9k | 3 |
| MiniMax M3 | ✗ | ✓ | 47.9 / 100 | 5.7k / 14k | 3 |
| Claude Haiku 4 5 | ✗ | ✗ | 31.3 / 100 | 7.9k / 1.8k | 3 |
| GLM 5.3 (OpenRouter) | ✗ | ✗ | 15.6 / 100 | 3.9k / 50k | 2 |