CG-AL-X187

hard Codeunits & Business Logic content f565447d37dc…

Description

Per-model results

Models that have attempted this task
ModelAttempt 1Attempt 2Avg scoreTokens / attemptRuns
Claude Opus 5✗✓81.3 / 1006.5k / 19k3
GPT-6 Luna✗✓81.3 / 1003.7k / 2.7k3
GPT-5.6 Luna✗✓75.0 / 1003.7k / 3.1k3
GPT-5.6 Sol✗✓75.0 / 1003.8k / 2.5k3
Gemini 3.8 Flash (OpenRouter)✗✓68.8 / 1004.4k / 22k3
Claude Opus 5.5✗✓64.6 / 1006.1k / 2.7k3
GPT-5.6 Terra✗✓64.6 / 1003.6k / 2.3k3
GPT-6.1 Sol✗✓64.6 / 1003.5k / 1.3k3
GPT-6 Sol✗✗62.5 / 1003.7k / 1.8k3
Claude Haiku 4 5✗✗52.1 / 1005.0k / 1.5k3
MiniMax M3✗✗41.7 / 1004.2k / 12k3
Claude Sonnet 5✗✗31.3 / 1005.6k / 3.8k3
GLM 5.3 (OpenRouter)✗✗31.3 / 1003.9k / 51k2