MCJudgeBench - Macro-F1: leaderboard
Constraint-level judging accuracy on MCJudgeBench (2026), where an LLM judge sees an instruction, a candidate response and its explicit constraint list and labels each of 653 constraints from 141 multi-constraint instructions as satisfied, partly satisfied or not satisfied. Macro-F1 over the three labels against human-validated labels, in percent; higher is better.
Metric: Macro-F1 (%, times 100) over the yes, partial and no classes of constraint-level verdicts: the judge sees an instruction, a candidate response and its explicit constraint list and labels each constraint yes, partial or no, over the 653 constraints of 141 multi-constraint instructions of MCJudgeBench; deterministic decoding at temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Sonnet 4.6 | Thinking | 63.7 | #179 |
| 2 | GPT-5.2 | 61.6 | #190 | |
| 3 | Claude Haiku 4.5 | Thinking | 60.3 | #587 |
| 4 | Gemini 3.1 Pro (Preview) | 59.8 | #102 | |
| 5 | Gemini 2.5 Flash Lite | Thinking | 56.9 | #972 |
| 6 | Qwen 3.5 4B | Non-reasoning | 52.9 | #1270 |
| 7 | Llama 3.2 3B Instruct | 44.1 | #7311 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mcjudgebench-macro-f1 · How It Works · Data refreshed daily, snapshot 2026-11-22.