CG-AL-X283

hard Codeunits & Business Logic content a7a1979bdd84…

Description

Per-model results

Models that have attempted this task
ModelAttempt 1Attempt 2Avg scoreTokens / attemptRuns
Claude Opus 5.5✓—100.0 / 10011k / 7.6k3
GPT-6.1 Sol✓—100.0 / 1006.5k / 3.8k3
Gemini 3.8 Flash (OpenRouter)✓—100.0 / 1007.6k / 40k3
Claude Opus 5✗✓81.3 / 10013k / 7.0k3
GPT-5.6 Sol✗✓81.3 / 1007.2k / 3.2k3
GPT-5.6 Terra✗✓81.3 / 1007.7k / 3.5k3
GPT-6 Luna✗✓81.3 / 1007.4k / 3.9k3
GPT-6 Sol✗✓81.3 / 1007.2k / 2.3k3
Claude Sonnet 5✗✓75.0 / 10014k / 15k3
GPT-5.6 Luna✗✓68.8 / 1008.0k / 3.9k3
Claude Haiku 4 5✗✗31.3 / 10012k / 2.1k3
MiniMax M3✗✗31.3 / 1007.9k / 27k3
GLM 5.3 (OpenRouter)✗✗0.0 / 1003.8k / 64k2