RankJudge - Biomedicine: leaderboard

RankJudge (2026) builds pairs of multi-turn, document-grounded conversations in which one conversation carries a single injected assistant failure; a judge must name the flawed conversation, its flawed turn and its failure type. Biomedical domain, conversations grounded in PubMedQA contexts. Bradley-Terry Elo on an open scale centred at 1500, from joint correctness on the retained pairs; higher is better.

Metric: Bradley-Terry Elo rating (open scale, mean strength mapped to 1500) of an LLM judge, fitted on joint correctness (the judge must pick the flawed conversation, its flawed turn and its failure type) over RankJudge pairs of multi-turn, document-grounded conversations in which exactly one conversation carries one injected assistant failure; pairs every judge answers alike and the top 5 percent hardest pairs are dropped; biomedical domain (194 pairs grounded in PubMedQA contexts); higher is better. Source: arxiv.org. Saturation forecast: Around June 2027. 20 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)1910#99
2Gemini 3 Flash1759#175
3Kimi K2.61732#192
4Qwen 3.6 Plus1719#238
5Claude Sonnet 4.61707#173
6Gemma 4 31B1671#382
7GLM-5.11671#198
8GPT-5.41617#135
9Qwen 3.5 397B A17B1597#264
10Claude Opus 4.71587#85
11Claude Haiku 4.51487#583
12Gemma 4 26B A4B1487#590
13Qwen 3.5 35B A3B1471#492
14Qwen 3.5 122B A10B1454#346
15DeepSeek V3.21370#419

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=rankjudge-biomedicine · How It Works · Data refreshed daily, snapshot 2026-11-21.