CIPHER Cross-Record Inference - MIMIC (Program-of-Thought): leaderboard

Metric: Harmonic answer score (%; per question the harmonic mean of token overlap with the reference and Gemini 2.5 Flash semantic acceptance, zero when rejected, averaged; MIMIC clinical records with redacted narratives; the full support-controlled context of 39-42 records including distractors; program-of-thought prompting; greedy decoding). Source: arxiv.org. Saturation forecast: Around 2029. 5 models tracked.

Top models

#ModelScore
1GPT-OSS-20B30.9
2Llama 3.3 70B Instruct23.4
3Qwen 3 Next 80B A3B21.5
4GPT-OSS-120B21.3
5Gemini 2.0 Flash17.6

Interactive version: theaggregate.ai/benchmark?slug=cipher-cross-record-inference-mimic-program-of-thought · How It Works · Data refreshed daily, snapshot 2026-09-26.