# Pelican Arena

> Kaggle's Pelican Arena asks every model for the same thing, an animated SVG of a pelican riding a bicycle, and people vote for the better drawing.

Canonical page: https://benchlm.ai/benchmarks/pelican-arena

- Category: [external](/external)
- Last updated: Latest evaluation November 13, 2026

Evaluation results published by [Kaggle](https://www.kaggle.com/benchmarks/kaggle/pelican-arena). undefined

A drawing qualifies only if the SVG renders; qualifying drawings then go to human votes. It tests drawing with code: the model writes SVG markup, not an image. 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/pelican-arena)
- [Published leaderboard data](https://www.kaggle.com/api/v1/benchmarks/kaggle/pelican-arena/leaderboard)

## About Pelican Arena

- Year: 2026
- Tasks: One prompt: an animated SVG of a pelican riding a bicycle, rated by human votes
- Format: Relative rating fitted to human pairwise votes
- Difficulty: Vector drawing and animation in code

A drawing qualifies only if the SVG renders; qualifying drawings then go to human votes. It tests drawing with code: the model writes SVG markup, not an image. 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.

Pelican Arena is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (60 source rows)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [GPT-6 Astra](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 445 votes; ±63; Evaluated 2026-11-13 | — | 1819 |
| 2 | [GPT-6.1 Sol](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 445 votes; ±62; Evaluated 2026-11-13 | — | 1787 |
| 3 | [GPT-6.1 Sol](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Xhigh Reasoning; 448 votes; ±61; Evaluated 2026-11-13 | — | 1785 |
| 4 | [GPT-6 Astra](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 440 votes; ±61; Evaluated 2026-11-13 | — | 1785 |
| 5 | [GPT-6 Astra](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Low Reasoning; 455 votes; ±60; Evaluated 2026-11-13 | — | 1756 |
| 6 | [Claude Opus 5.5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 342 votes; ±63; Evaluated 2026-11-13 | — | 1736 |
| 7 | [Claude Sonnet 5.5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 353 votes; ±62; Evaluated 2026-11-13 | — | 1726 |
| 8 | [Claude Opus 5.5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Xhigh Reasoning; 442 votes; ±58; Evaluated 2026-11-13 | — | 1696 |
| 9 | [GPT-6 Sol](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 441 votes; ±58; Evaluated 2026-11-13 | — | 1674 |
| 10 | [Claude Fable 5.1](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 439 votes; ±58; Evaluated 2026-11-13 | — | 1672 |
| 11 | [Gemini 4 Argon](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 436 votes; ±58; Evaluated 2026-11-13 | — | 1664 |
| 12 | [GPT-5.6 Sol](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 443 votes; ±57; Evaluated 2026-11-13 | — | 1640 |
| 13 | [Gemini 4 Argon](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Low Reasoning; 438 votes; ±57; Evaluated 2026-11-12 | — | 1633 |
| 14 | [Gemini 4 Carbon](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 258 votes; ±64; Evaluated 2026-11-13 | — | 1600 |
| 15 | [GLM-5.3-Flash](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | 440 votes; ±57; Evaluated 2026-11-13 | — | 1599 |
| 16 | [Qwen 3.8 Max](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Xhigh Reasoning; 442 votes; ±56; Evaluated 2026-11-13 | — | 1592 |
| 17 | [GPT-5.6 Sol](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Xhigh Reasoning; 442 votes; ±56; Evaluated 2026-11-13 | — | 1588 |
| 18 | [Claude Opus 5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Xhigh Reasoning; 440 votes; ±56; Evaluated 2026-11-13 | — | 1583 |
| 19 | [Gemini 3.8 Flash](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 586 votes; ±54; Evaluated 2026-11-13 | — | 1570 |
| 20 | [Gemini 3.8 Flash](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Medium Reasoning; 593 votes; ±53; Evaluated 2026-11-13 | — | 1569 |
| 21 | [GLM-5.3](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 444 votes; ±56; Evaluated 2026-11-13 | — | 1568 |
| 22 | [Claude Opus 5.5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 443 votes; ±56; Evaluated 2026-11-13 | — | 1568 |
| 23 | [Claude Opus 5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 437 votes; ±56; Evaluated 2026-11-12 | — | 1561 |
| 24 | [Claude Opus 5.5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Medium Reasoning; 347 votes; ±59; Evaluated 2026-11-13 | — | 1552 |
| 25 | [GPT-6 Sol](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 455 votes; ±56; Evaluated 2026-11-13 | — | 1549 |
| 26 | [GPT-6 Luna](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 441 votes; ±56; Evaluated 2026-11-13 | — | 1536 |
| 27 | [GPT-5.6 Sol](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Medium Reasoning; 443 votes; ±56; Evaluated 2026-11-13 | — | 1506 |
| 28 | [Gemini 3.6 Flash](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Medium Reasoning; 448 votes; ±56; Evaluated 2026-11-13 | — | 1494 |
| 29 | [Claude Sonnet 5.5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 435 votes; ±56; Evaluated 2026-11-13 | — | 1494 |
| 30 | [Kimi K3](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 436 votes; ±56; Evaluated 2026-11-13 | — | 1494 |
| 31 | [Qwen 3.8 Max](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | 450 votes; ±56; Evaluated 2026-11-13 | — | 1490 |
| 32 | [Claude Fable 5.1](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 434 votes; ±56; Evaluated 2026-11-12 | — | 1489 |
| 33 | [GLM-5.3](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 451 votes; ±56; Evaluated 2026-11-13 | — | 1473 |
| 34 | [Grok 4.6](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 344 votes; ±59; Evaluated 2026-11-11 | — | 1468 |
| 35 | [Kimi K3](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Medium Reasoning; 440 votes; ±56; Evaluated 2026-11-13 | — | 1468 |
| 36 | [Qwen 3.8 Max](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Medium Reasoning; 445 votes; ±56; Evaluated 2026-11-13 | — | 1467 |
| 37 | [GPT-6 Luna](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 435 votes; ±56; Evaluated 2026-11-13 | — | 1465 |
| 38 | [GPT-5.6 Sol](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 443 votes; ±56; Evaluated 2026-11-13 | — | 1464 |
| 39 | [Claude Opus 5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 444 votes; ±56; Evaluated 2026-11-13 | — | 1457 |
| 40 | [Gemini 3.6 Flash](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 439 votes; ±56; Evaluated 2026-11-13 | — | 1452 |
| 41 | [GLM-5.3](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Medium Reasoning; 459 votes; ±56; Evaluated 2026-11-13 | — | 1428 |
| 42 | [Claude Fable 5.1](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Low Reasoning; 440 votes; ±56; Evaluated 2026-11-13 | — | 1422 |
| 43 | [GPT-5.6 Luna](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Max Reasoning; 451 votes; ±56; Evaluated 2026-11-13 | — | 1420 |
| 44 | [Grok 4.6](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Xhigh Reasoning; 343 votes; ±59; Evaluated 2026-11-12 | — | 1420 |
| 45 | [Kimi K3](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 432 votes; ±57; Evaluated 2026-11-12 | — | 1417 |
| 46 | [Qwen 3.8 Max](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Low Reasoning; 438 votes; ±56; Evaluated 2026-11-13 | — | 1400 |
| 47 | [Claude Opus 5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Medium Reasoning; 444 votes; ±57; Evaluated 2026-11-13 | — | 1371 |
| 48 | [Grok 4.5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 443 votes; ±57; Evaluated 2026-11-13 | — | 1358 |
| 49 | [GPT-5.6 Terra](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | GPT 5.6 Terra Max Reasoning; 437 votes; ±58; Evaluated 2026-11-13 | — | 1342 |
| 50 | [GPT-5.6 Luna](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | XHigh Reasoning; 440 votes; ±57; Evaluated 2026-11-13 | — | 1341 |
| 51 | [Claude Haiku 5.5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | 442 votes; ±58; Evaluated 2026-11-13 | — | 1325 |
| 52 | [Gemini 3.8 Flash](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Low Reasoning; 95 votes; ±91; Evaluated 2026-11-13 | — | 1310 |
| 53 | [Grok 4.7](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Xhigh Reasoning; 442 votes; ±58; Evaluated 2026-11-12 | — | 1304 |
| 54 | [GPT-5.6 Luna](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 447 votes; ±59; Evaluated 2026-11-13 | — | 1279 |
| 55 | [GPT-5.6 Terra](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Medium Reasoning; 448 votes; ±59; Evaluated 2026-11-13 | — | 1267 |
| 56 | [GPT-5.6 Terra](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | XHigh Reasoning; 436 votes; ±60; Evaluated 2026-11-13 | — | 1252 |
| 57 | [GPT-5.6 Terra](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 445 votes; ±60; Evaluated 2026-11-13 | — | 1234 |
| 58 | [Claude Sonnet 5](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | 435 votes; ±61; Evaluated 2026-11-13 | — | 1229 |
| 59 | [GPT-5.6 Luna](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | Medium Reasoning; 440 votes; ±62; Evaluated 2026-11-13 | — | 1208 |
| 60 | [Gemini 3.5 Flash-Lite](https://www.kaggle.com/benchmarks/kaggle/pelican-arena) | High Reasoning; 437 votes; ±63; Evaluated 2026-11-13 | — | 1186 |

## FAQ

### What does Pelican Arena measure?

Kaggle's Pelican Arena asks every model for the same thing, an animated SVG of a pelican riding a bicycle, and people vote for the better drawing.

### Which source row has the highest reported Pelican Arena value?

GPT-6 Astra has the highest reported Pelican Arena value at 1819. A rating gap smaller than the two rows' intervals is not a reliable difference.

### How many models are evaluated on Pelican Arena?

The Latest evaluation November 13, 2026 contains 60 AI models.

### Does Pelican Arena affect BenchLM's overall score?

Not directly. Pelican Arena is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.