CG-AL-X271

hard Codeunits & Business Logic content c78fb44a91c8…

Description

Per-model results

Models that have attempted this task
ModelAttempt 1Attempt 2Avg scoreTokens / attemptRuns
Claude Opus 5✗✓81.3 / 10015k / 16k3
Claude Opus 5.5✗✓81.3 / 10014k / 6.1k3
GPT-5.6 Terra✗✓81.3 / 1008.5k / 4.7k3
GPT-6 Sol✗✓81.3 / 1008.0k / 4.1k3
GPT-6.1 Sol✗✓81.3 / 1008.0k / 3.1k3
Gemini 3.8 Flash (OpenRouter)✗✓81.3 / 1009.3k / 25k3
GPT-5.6 Sol✗✓75.0 / 1008.4k / 4.7k3
GPT-6 Luna✗✗62.5 / 1009.2k / 6.8k3
GPT-5.6 Luna✗✗52.1 / 1008.7k / 5.4k3
Claude Sonnet 5✗✗31.3 / 10014k / 12k3
Claude Haiku 4 5✗✗20.8 / 10012k / 3.5k3
GLM 5.3 (OpenRouter)✗✗15.6 / 1006.8k / 63k2
MiniMax M3✗✗10.4 / 1003.1k / 14k3