CG-AL-X276

hard Codeunits & Business Logic content b8bbb1279200…

Description

Per-model results

Models that have attempted this task
ModelAttempt 1Attempt 2Avg scoreTokens / attemptRuns
Claude Opus 5✗✓81.3 / 10012k / 7.2k3
Claude Opus 5.5✗✓81.3 / 10012k / 4.9k3
Claude Sonnet 5✗✓81.3 / 10012k / 16k3
GPT-6 Luna✗✓81.3 / 1007.4k / 4.2k3
GPT-6 Sol✗✓81.3 / 1007.6k / 2.6k3
GPT-6.1 Sol✗✓81.3 / 1006.8k / 1.8k3
GLM 5.3 (OpenRouter)✗✓81.3 / 1007.1k / 33k2
GPT-5.6 Terra✗✓75.0 / 1008.2k / 3.6k3
GPT-5.6 Luna✗✓68.8 / 1008.0k / 3.6k3
GPT-5.6 Sol✗✓68.8 / 1007.3k / 3.3k3
Claude Haiku 4 5✗✗62.5 / 10012k / 1.8k3
Gemini 3.8 Flash (OpenRouter)✗✓58.3 / 1009.2k / 33k3
MiniMax M3✗✓47.9 / 1005.5k / 17k3