HumorRank - SemEval-2026 MWAHAHA: leaderboard

HumorRank (2026) ranks humor generation with a full round-robin tournament of pairwise joke comparisons judged by Llama 3.3 70B Instruct. This board is the Bradley-Terry rating on SemEval-2026 MWAHAHA headline prompts, an open Elo-style scale whose ratings average 1000; higher is better.

Metric: Bradley-Terry rating (open scale, mean about 1000) from a full round-robin of pairwise joke comparisons on SemEval-2026 MWAHAHA, 10,800 judgments, judged by Llama 3.3 70B Instruct; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-51307.5#178
2Kimi K21156.9#443
3Gemini 2.5 Pro1115.1#276
4HumorGen-7B1092.8
5Claude 3.5 Haiku1037.5#1580
6GPT-OSS-120B1015#704
7Qwen 3 32B976.9#972
8Llama 3.3 70B761#1514
9Qwen 2.5 7B Instruct537.4#2723

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

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