CG-AL-X270

hard Codeunits & Business Logic content 0658ef9316eb…

Description

Per-model results

Models that have attempted this task
ModelAttempt 1Attempt 2Avg scoreTokens / attemptRuns
Claude Opus 5✗✓81.3 / 10015k / 19k3
Claude Opus 5.5✗✓81.3 / 10014k / 5.7k3
GPT-6 Sol✗✓81.3 / 1007.8k / 3.2k3
GPT-6.1 Sol✗✓81.3 / 1007.7k / 2.7k3
Gemini 3.8 Flash (OpenRouter)✗✓81.3 / 1009.1k / 34k3
GPT-5.6 Sol✗✓75.0 / 1008.3k / 4.6k3
GPT-6 Luna✗✓75.0 / 1008.4k / 4.3k3
Claude Sonnet 5✗✓68.8 / 10016k / 17k3
GPT-5.6 Terra✗✓64.6 / 1008.9k / 4.0k3
Claude Haiku 4 5✗✗62.5 / 10013k / 2.1k3
GPT-5.6 Luna✗✗62.5 / 1009.1k / 3.1k3
MiniMax M3✗✗62.5 / 10011k / 22k3
GLM 5.3 (OpenRouter)✗✗15.6 / 1006.9k / 60k2