MemeBench - Reasoning: leaderboard
MemeBench (2026) asks vision-language models to explain 1,253 Chinese and English memes about anime, comics, games and online subcultures from the image alone, checked against VIKR checklists of visual clues, identity links, knowledge units and reasoning under two judges. This board is the coverage of the reasoning-mechanism checklist items, in percent; higher is better.
Metric: Reasoning-mechanism coverage (%) on 1,253 Chinese and English memes centred on anime, comics, games and online subcultures, explained closed-book from the image; scored against VIKR checklists under the intersection of Gemini-3.1-Pro and GPT-5.1 judges, unscored responses counted as failures. Source: arxiv.org. Saturation forecast: Around February 2027. 26 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 76.7 | #94 |
| 2 | Gemini 3 Flash | 70.3 | #164 |
| 3 | GPT-5.6 Sol | 60.7 | #30 |
| 4 | Kimi K2.5 | 58.7 | #256 |
| 5 | Claude Opus 5 | 57.9 | #22 |
| 6 | Qwen 3.6 Plus | 47.7 | #222 |
| 7 | GPT-5.6 Terra | 46.9 | #62 |
| 8 | Claude Sonnet 5 | 35.6 | #111 |
| 9 | GPT-5.6 Luna | 35 | #121 |
| 10 | Qwen 3.6 Flash | 29 | #424 |
| 11 | MiMo-V2.5 | 28.3 | #354 |
| 12 | Qwen 3 VL 235B A22B Instruct | 27.3 | #522 |
| 13 | Qwen 3 VL 235B A22B (Thinking) | 24.7 | #451 |
| 14 | Qwen 3 VL 32B Instruct | 20 | #585 |
| 15 | Qwen 3 VL 32B (Thinking) | 19.7 | #559 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=memebench-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-13.