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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 1307.5 | #178 |
| 2 | Kimi K2 | 1156.9 | #443 |
| 3 | Gemini 2.5 Pro | 1115.1 | #276 |
| 4 | HumorGen-7B | 1092.8 | |
| 5 | Claude 3.5 Haiku | 1037.5 | #1580 |
| 6 | GPT-OSS-120B | 1015 | #704 |
| 7 | Qwen 3 32B | 976.9 | #972 |
| 8 | Llama 3.3 70B | 761 | #1514 |
| 9 | Qwen 2.5 7B Instruct | 537.4 | #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.