CG-AL-X185

hard Codeunits & Business Logic content aec2cc986878…

Summary

Exact model prompt

Per-model results

Models that have attempted this task
ModelAttempt 1Attempt 2Avg scoreTokens / attemptRuns
GPT-6 Luna✗✓75.0 / 1003.4k / 2.0k3
GPT-6.1 Sol✗✓75.0 / 1002.7k / 8123
Claude Sonnet 5✗✓68.8 / 1005.9k / 4.3k3
Claude Opus 5✗✗62.5 / 1005.9k / 3.9k3
Claude Opus 5.5✗✗62.5 / 1004.6k / 1.6k3
GPT-5.6 Luna✗✗62.5 / 1003.4k / 1.6k3
GPT-5.6 Sol✗✗62.5 / 1003.2k / 1.5k3
GPT-5.6 Terra✗✗62.5 / 1003.4k / 1.8k3
GPT-6 Sol✗✗62.5 / 1003.2k / 9093
Gemini 3.8 Flash (OpenRouter)✗✗62.5 / 1003.1k / 8.7k3
GLM 5.3 (OpenRouter)✗✓56.3 / 1003.5k / 49k2
Claude Haiku 4 5✗✗52.1 / 1005.0k / 8103
MiniMax M3✗✓47.9 / 1003.7k / 5.8k3