CG-AL-X194

hard Codeunits & Business Logic content 6e4c947fcb8a…

Description

Per-model results

Models that have attempted this task
ModelAttempt 1Attempt 2Avg scoreTokens / attemptRuns
Claude Opus 5.5✗✓81.3 / 1008.9k / 3.4k3
GPT-5.6 Sol✗✓81.3 / 1005.1k / 3.5k3
GPT-5.6 Terra✗✓81.3 / 1005.0k / 2.5k3
GPT-6 Sol✗✓81.3 / 1005.0k / 1.9k3
GPT-6.1 Sol✗✓81.3 / 1005.0k / 1.8k3
Claude Opus 5✗✓75.0 / 1009.2k / 11k3
GPT-6 Luna✗✓75.0 / 1005.0k / 2.9k3
GPT-5.6 Luna✗✓68.8 / 1005.0k / 3.0k3
Gemini 3.8 Flash (OpenRouter)✗✓64.6 / 1005.7k / 24k3
Claude Haiku 4 5✗✗62.5 / 1007.7k / 2.1k3
Claude Sonnet 5✗✓58.3 / 1009.1k / 8.7k3
MiniMax M3✗✗41.7 / 1004.4k / 15k3
GLM 5.3 (OpenRouter)✗✗15.6 / 1005.3k / 62k2