RankJudge - Machine Learning: 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. Machine-learning domain, conversations grounded in computer-science papers. 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; machine-learning domain (240 pairs grounded in CS papers); higher is better. Source: arxiv.org. Saturation forecast: Around June 2027. 20 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 1992 | #99 |
| 2 | Claude Sonnet 4.6 | 1755 | #173 |
| 3 | Kimi K2.6 | 1743 | #192 |
| 4 | Gemma 4 31B | 1708 | #382 |
| 5 | Gemini 3 Flash | 1665 | #175 |
| 6 | Qwen 3.6 Plus | 1665 | #238 |
| 7 | GLM-5.1 | 1665 | #198 |
| 8 | Qwen 3.5 397B A17B | 1590 | #264 |
| 9 | GPT-5.4 | 1581 | #135 |
| 10 | Claude Opus 4.7 | 1523 | #85 |
| 11 | Claude Haiku 4.5 | 1492 | #583 |
| 12 | Gemma 4 26B A4B | 1428 | #590 |
| 13 | Qwen 3.5 122B A10B | 1381 | #346 |
| 14 | Qwen 3.5 35B A3B | 1349 | #492 |
| 15 | GPT-5.4 Mini | 1343 | #406 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=rankjudge-machine-learning · How It Works · Data refreshed daily, snapshot 2026-11-21.