CG-AL-X249

hard Codeunits & Business Logic content 2437e9f9a4e0…

Description

Per-model results

Models that have attempted this task
ModelAttempt 1Attempt 2Avg scoreTokens / attemptRuns
Claude Opus 5.5✗✓81.3 / 1008.3k / 3.9k3
GPT-5.6 Luna✗✓81.3 / 1005.2k / 3.4k3
GPT-6 Luna✗✓81.3 / 1004.8k / 3.4k3
GPT-6.1 Sol✗✓81.3 / 1004.7k / 1.8k3
Gemini 3.8 Flash (OpenRouter)✗✓81.3 / 1005.5k / 26k3
Claude Opus 5✗✓75.0 / 1008.4k / 17k3
GPT-5.6 Sol✗✓75.0 / 1004.8k / 2.9k3
GPT-5.6 Terra✗✓75.0 / 1005.1k / 3.0k3
GPT-6 Sol✗✓75.0 / 1004.8k / 2.2k3
Claude Sonnet 5✗✓68.8 / 1008.4k / 9.8k3
Claude Haiku 4 5✗✗62.5 / 1006.6k / 1.5k3
MiniMax M3✗✓58.3 / 1004.2k / 18k3
GLM 5.3 (OpenRouter)✗✗31.3 / 1005.0k / 60k2