Dual-exception recall and exposure accuracy vary meaningfully across model families

While detection accuracy is near-equivalent across all evaluated models, two sub-metrics show meaningful model-family divergence. Dual-exception recall: GPT-4o and both Gemini models catch all secondary exceptions (100%) while Claude Sonnet misses the second exception in ~1 in 8 dual-exception cases (87.4%). Exposure accuracy: Gemini 2.5 Pro 76.0%, Gemini 2.5 Flash 79.5%, GPT-4o 66.1%, Claude 64.3% (rescored 2026-10-12 on the corrected key; for the later runs, the prompt in our run scripts contained the same unit error, and these runs' answers are consistent with it, so 7 cases removed, 57 cases). The dual-exception gap survives prompt correction and are now confirmed across five evaluations from three labs.