# Joke Arena > Kaggle's Joke Arena asks models for an original joke on 100 topics, and people vote for the funnier one. Canonical page: https://benchlm.ai/benchmarks/joke-arena - Category: [external](/external) - Last updated: Latest evaluation November 12, 2026 Evaluation results published by [Kaggle](https://www.kaggle.com/benchmarks/kaggle/joke-arena). undefined A response qualifies if it is a family-friendly joke of 3 to 150 words. Kaggle shows two anonymous outputs for the same prompt and a person picks the better one. The Arena column is the relative rating Kaggle fits to those votes, published with an interval; it is not a percentage. The rating moves as votes arrive, and Kaggle publishes no confidence level for its interval. Rows with few votes have wide intervals, so neighbouring models are often not separable. Voters are self-selected Kaggle visitors. The board declares no license; we keep published aggregates with attribution and no task or output contents. A rating gap smaller than the two rows' intervals is not a reliable difference. - [Kaggle arena leaderboard](https://www.kaggle.com/benchmarks/kaggle/joke-arena) - [Published leaderboard data](https://www.kaggle.com/api/v1/benchmarks/kaggle/joke-arena/leaderboard) ## About Joke Arena - Year: 2026 - Tasks: 100 joke prompts in 10 categories, rated by human votes - Format: Relative rating fitted to human pairwise votes - Difficulty: Humour writing A response qualifies if it is a family-friendly joke of 3 to 150 words. Kaggle shows two anonymous outputs for the same prompt and a person picks the better one. The Arena column is the relative rating Kaggle fits to those votes, published with an interval; it is not a percentage. These results are display-only and do not enter overall or category rankings. Joke Arena is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula. ## Leaderboard (27 source rows) | Rank | Model | Configuration | Creator | Score | |------|-------|---------------|---------|-------| | 1 | [Kimi K3](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Max Reasoning; 20 votes; ±153; Evaluated 2026-11-12 | — | 1573 | | 2 | [Gemini 3.1 Pro Preview](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | High Reasoning; 22 votes; ±148; Evaluated 2026-11-12 | — | 1568 | | 3 | [GPT-6 Astra](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Max Reasoning; 69 votes; ±104; Evaluated 2026-11-12 | — | 1564 | | 4 | [Gemini 3.8 Flash](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | High Reasoning; 36 votes; ±126; Evaluated 2026-11-12 | — | 1557 | | 5 | [Claude Sonnet 5.5](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Max Reasoning; 61 votes; ±107; Evaluated 2026-11-12 | — | 1549 | | 6 | [Claude Fable 5.1](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Max Reasoning; 65 votes; ±105; Evaluated 2026-11-12 | — | 1541 | | 7 | [GLM-5.3](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Max Reasoning; 67 votes; ±103; Evaluated 2026-11-12 | — | 1537 | | 8 | [GPT-5.6 Sol](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Max Reasoning; 30 votes; ±132; Evaluated 2026-11-12 | — | 1520 | | 9 | [GPT-6.1 Sol](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Max Reasoning; 68 votes; ±103; Evaluated 2026-11-12 | — | 1519 | | 10 | [GPT-5.6 Terra](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | High Reasoning; 61 votes; ±106; Evaluated 2026-11-12 | — | 1517 | | 11 | [Claude Opus 5](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Max Reasoning; 27 votes; ±136; Evaluated 2026-11-12 | — | 1515 | | 12 | [Claude Opus 5.5](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Max Reasoning; 62 votes; ±106; Evaluated 2026-11-12 | — | 1508 | | 13 | [GPT-5](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | High Reasoning; 25 votes; ±140; Evaluated 2026-11-12 | — | 1505 | | 14 | [Gemini 4 Argon](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | High Reasoning; 69 votes; ±103; Evaluated 2026-11-12 | — | 1501 | | 15 | [GPT-5.5](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | GPT-5.5 High Reasoning; 65 votes; ±105; Evaluated 2026-11-12 | — | 1499 | | 16 | [Claude Opus 4.7](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | High Reasoning; 18 votes; ±157; Evaluated 2026-11-12 | — | 1487 | | 17 | [GPT-6 Luna](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Max Reasoning; 67 votes; ±103; Evaluated 2026-11-12 | — | 1486 | | 18 | [GPT-5 Pro](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | High Reasoning; 35 votes; ±126; Evaluated 2026-11-12 | — | 1486 | | 19 | [Grok 4.7](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Xhigh Reasoning; 63 votes; ±105; Evaluated 2026-11-12 | — | 1482 | | 20 | [GPT-5.6 Terra](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | GPT 5.6 Terra Max Reasoning; 59 votes; ±108; Evaluated 2026-11-12 | — | 1478 | | 21 | [Grok 4.6](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | High Reasoning; 28 votes; ±135; Evaluated 2026-11-12 | — | 1469 | | 22 | [GPT-5.4](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Xhigh Reasoning; 22 votes; ±148; Evaluated 2026-11-12 | — | 1460 | | 23 | [Qwen 3.8 Max](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Xhigh Reasoning; 75 votes; ±101; Evaluated 2026-11-12 | — | 1457 | | 24 | [Claude Opus 4.7](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Max Reasoning; 30 votes; ±133; Evaluated 2026-11-12 | — | 1455 | | 25 | [GPT-5.2](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | Xhigh Reasoning; 24 votes; ±143; Evaluated 2026-11-12 | — | 1455 | | 26 | [Claude Sonnet 5](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | High Reasoning; 30 votes; ±135; Evaluated 2026-11-12 | — | 1417 | | 27 | [Gemini 4 Carbon](https://www.kaggle.com/benchmarks/kaggle/joke-arena) | High Reasoning; 10 votes; ±194; Evaluated 2026-11-12 | — | 1395 | ## FAQ ### What does Joke Arena measure? Kaggle's Joke Arena asks models for an original joke on 100 topics, and people vote for the funnier one. ### Which source row has the highest reported Joke Arena value? Kimi K3 has the highest reported Joke Arena value at 1573. A rating gap smaller than the two rows' intervals is not a reliable difference. ### How many models are evaluated on Joke Arena? The Latest evaluation November 12, 2026 contains 27 AI models. ### Does Joke Arena affect BenchLM's overall score? Not directly. Joke Arena is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.