Benchmark Almanac

MWAHAHA

Gemini 2.5 Flash (snapshot unspecified) 1,084 tops its leaderboard
Not in model cards

Models write jokes from word pairs or news headlines in English, Spanish, and Chinese. They also caption animated GIFs in English.

Readers choose the funnier of two responses to the same prompt. The organizers publish five separate rankings with uncertainty intervals.

Released
July 2025
Kind
Creative writing
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Measures
Preference
Language
English, Spanish, Chinese
In and out
Text, Video → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Vision
12
Entries on its own leaderboard, 0 models we track

Gemini 2.5 Flash (snapshot unspecified) tops the leaderboard with 1,084 No scores yet

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as SLPG_FJWU_Insa + Phi-2, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.

Bars start at 850.

  1. 1 Gemini 2.5 Flash (snapshot unspecified) Zero-shot 1,084
  2. 2 SLPG_FJWU_Insa + Phi-2 1,080
  3. 3 Qwen2.5-14B-Instruct + Mistral-7B-Instruct-v0.1 1,042
  4. 4 DeepSeek-R1 (snapshot unspecified) 1,034
  5. 5 AI4PC + Llama 3.1-8B 1,020
  6. 6 j10official (Gemma 3 27B + Nemotron) 1,005
  7. 7 Gemma 1,002
  8. 8 YNWA_AZ (Llama 3-8B + BLIP + TinyLlama) 997
  9. 9 hugang11 + Qwen2.5-7B 991
  10. 10 Edward Ajayi + Qwen2.5-7B 950
  11. 11 deepgpt + Qwen2.5-3B 903
  12. 12 Qwen2.5-3B-Instruct + Salamandra-2B-Instruct 871

Source: Official MWAHAHA leaderboard

#EntryScoreSettingSubmitted byDateSource
1 Gemini 2.5 Flash (snapshot unspecified) 1,084 Zero-shot Organizers Official leaderboard
2 SLPG_FJWU_Insa + Phi-2 1,080 SLPG_FJWU_Insa Dec 2023 Official leaderboard
3 Qwen2.5-14B-Instruct + Mistral-7B-Instruct-v0.1 1,042 DUTH DUTH Official leaderboard
4 DeepSeek-R1 (snapshot unspecified) 1,034 Lattice Lattice Official leaderboard
5 AI4PC + Llama 3.1-8B 1,020 AI4PC Jul 2024 Official leaderboard
6 j10official (Gemma 3 27B + Nemotron) 1,005 j10official Mar 2025 Official leaderboard
7 Gemma 1,002 FunnyBorg FunnyBorg Official leaderboard
8 YNWA_AZ (Llama 3-8B + BLIP + TinyLlama) 997 YNWA_AZ Apr 2024 Official leaderboard
9 hugang11 + Qwen2.5-7B 991 hugang11 Sep 2024 Official leaderboard
10 Edward Ajayi + Qwen2.5-7B 950 Edward Ajayi Sep 2024 Official leaderboard
11 deepgpt + Qwen2.5-3B 903 deepgpt Sep 2024 Official leaderboard
12 Qwen2.5-3B-Instruct + Salamandra-2B-Instruct 871 CUET_clashing CUET_clashing Official leaderboard
#ModelScoreSettingSubmitted byDateSource

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Writing and taste

All 65 in Writing and taste
  • Design Bench (Moonshot) In use Models make graphic designs from direct prompts or few-shot reference images. An automated grader rates the results as Elo scores. Kimi K3.1 Pro 957
  • WritingBench Fading Models complete 1,000 real-world writing requests across 6 domains and 100 subdomains. A judge model scores each reply on five query-specific criteria. GPT-5 83.9
  • Creative Writing (MiniMax in-house) Only in system cards Models write creative pieces for real Hailuo AI user requests. Automatic assessments score the writing. MiniMax-Text-01 81.3%
  • DeepSeek Chinese functional writing evaluation Only in system cards Models answer 3,170 everyday Chinese writing prompts such as reports, emails and speeches. Pairwise judging against a baseline model gives a win rate. DeepSeek-V4-Pro 62.6%
  • Slide generation human evaluation (Z.ai) Only in system cards People compare HTML slide decks from two models on content, layout and visual quality. Metric is overall win rate. GLM-5 67.5%
  • Task-dependent output homogenization evaluation Only in system cards Models answer prompts several times. A judge scores functional diversity where it is wanted and consistency where one answer is right. Muse Spark 0.21

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (12 entries).
  • Pass Models scored 12 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as an Elo rating, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on pln-fing-udelar.github.io: 7 rows for models we track and 5 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check