Kaggle SVG Arena
Models draw SVG images from 120 prompts across twelve categories. Submissions must render and satisfy the drawing rule for the prompt. Votes determine the arena rating.
Kaggle publishes scores for 25 distinct model versions.
- Made by
- Kaggle
- Released
- October 2026
- Kind
- Web and app front ends
- Level
- University
- Scored
- Ranked by votes
- Answers
- Code
- Tasks
- All public
- Measures
- Preference
- Language
- English
- Interaction
- Single turn
- Refresh
- Live
- Run by
- A host
- In views
- Kept fresh
- Strongest model tested
-
Gemini 4 Carbon #3 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 1,699
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
- 1,699 Claude Opus 5.5
- 1,687
Gemini 4 Argon
- 1,672 GPT-6 Astra
- 1,657 GPT-6.1 Sol
- 1,632
Gemini 4 Carbon
- 1,617 GPT-6 Sol
- 1,587 Claude Opus 5
- 1,564
Gemini 3.8 Flash
- 1,559 Claude Fable 5.1
- 1,547
Qwen 3.8 Max
- 1,536 Claude Sonnet 5.5
- 1,532 GPT-5.6 Sol
- 1,496 Grok 4.7
- 1,468
Gemini 3.6 Flash
- 1,455 GLM-5.3-Flash
- 1,455 GLM-5.3
- 1,437 GPT-6 Luna
- 1,419 GPT-5.6 Terra
- 1,418 GPT-5.6 Luna
- 1,399 Grok 4.6
- 1,393 Kimi K3
- 1,335
Gemini 3.5 Flash-Lite
- 1,334 Grok 4.5
- 1,309 Claude Sonnet 5
- 1,305 Claude Haiku 5.5
Bars start at 1,300.
- 1 Claude Opus 5.5 Claude Opus 5.5 Max Reasoning 1,699
- 2
Gemini 4 Argon Gemini 4 Argon High Reasoning 1,687
- 3 GPT-6 Astra GPT-6 Astra Max Reasoning 1,672
- 4 GPT-6.1 Sol GPT-6.1 Sol Max Reasoning 1,657
- 5
Gemini 4 Carbon Gemini 4 Carbon High Reasoning 1,632
- 6 GPT-6 Sol GPT-6 Sol Max Reasoning 1,617
- 7 Claude Opus 5 Claude Opus 5 Max Reasoning 1,587
- 8
Gemini 3.8 Flash Gemini 3.8 Flash High Reasoning 1,564
- 9 Claude Fable 5.1 Claude Fable 5.1 Max Reasoning 1,559
- 10
Qwen 3.8 Max Qwen 3.8 Max Xhigh Reasoning 1,547
- 11 Claude Sonnet 5.5 Claude Sonnet 5.5 Max Reasoning 1,536
- 12 GPT-5.6 Sol GPT-5.6 Sol Max Reasoning 1,532
- 13 Grok 4.7 Grok 4.7 Xhigh Reasoning 1,496
- 14
Gemini 3.6 Flash Gemini 3.6 Flash High Reasoning 1,468
- 15 GLM-5.3-Flash 1,455
- 16 GLM-5.3 GLM-5.3 Max Reasoning 1,455
- 17 GPT-6 Luna GPT-6 Luna Max Reasoning 1,437
- 18 GPT-5.6 Terra GPT 5.6 Terra Max Reasoning 1,419
- 19 GPT-5.6 Luna GPT-5.6 Luna Max Reasoning 1,418
- 20 Grok 4.6 Grok 4.6 Xhigh Reasoning 1,399
- 21 Kimi K3 Kimi K3 Max Reasoning 1,393
- 22
Gemini 3.5 Flash-Lite Gemini 3.5 Flash-Lite High Reasoning 1,335
- 23 Grok 4.5 Grok 4.5 High Reasoning 1,334
- 24 Claude Sonnet 5 1,309
- 25 Claude Haiku 5.5 1,305
Source: Official Kaggle SVG Arena leaderboard
| # | Model | Score ± | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 1,699 ±90.1 | Claude Opus 5.5 Max Reasoning | Sep 2026 | Nov 2026 | Official leaderboard |
| 2 | | 1,687 ±91.2 | Gemini 4 Argon High Reasoning | Sep 2026 | Nov 2026 | Official leaderboard |
| 3 | GPT-6 Astra | 1,672 ±88.8 | GPT-6 Astra Max Reasoning | Sep 2026 | Nov 2026 | Official leaderboard |
| 4 | GPT-6.1 Sol | 1,657 ±88.8 | GPT-6.1 Sol Max Reasoning | Sep 2026 | Nov 2026 | Official leaderboard |
| 5 | | 1,632 ±114.4 | Gemini 4 Carbon High Reasoning | Oct 2026 | Nov 2026 | Official leaderboard |
| 6 | GPT-6 Sol | 1,617 ±89.6 | GPT-6 Sol Max Reasoning | Sep 2026 | Nov 2026 | Official leaderboard |
| 7 | Claude Opus 5 | 1,587 ±85.5 | Claude Opus 5 Max Reasoning | Jul 2026 | Nov 2026 | Official leaderboard |
| 8 | | 1,564 ±85.5 | Gemini 3.8 Flash High Reasoning | Sep 2026 | Nov 2026 | Official leaderboard |
| 9 | Claude Fable 5.1 | 1,559 ±86.3 | Claude Fable 5.1 Max Reasoning | Sep 2026 | Nov 2026 | Official leaderboard |
| 10 | | 1,547 ±96.5 | Qwen 3.8 Max Xhigh Reasoning | Aug 2026 | Nov 2026 | Official leaderboard |
| 11 | Claude Sonnet 5.5 | 1,536 ±99.1 | Claude Sonnet 5.5 Max Reasoning | Sep 2026 | Nov 2026 | Official leaderboard |
| 12 | GPT-5.6 Sol | 1,532 ±87 | GPT-5.6 Sol Max Reasoning | Jul 2026 | Nov 2026 | Official leaderboard |
| 13 | Grok 4.7 | 1,496 ±87.4 | Grok 4.7 Xhigh Reasoning | Sep 2026 | Nov 2026 | Official leaderboard |
| 14 | | 1,468 ±86.5 | Gemini 3.6 Flash High Reasoning | Jul 2026 | Nov 2026 | Official leaderboard |
| 15 | GLM-5.3-Flash | 1,455 ±85.5 | Aug 2026 | Nov 2026 | Official leaderboard | |
| 16 | GLM-5.3 | 1,455 ±87.6 | GLM-5.3 Max Reasoning | Aug 2026 | Nov 2026 | Official leaderboard |
| 17 | GPT-6 Luna | 1,437 ±87.3 | GPT-6 Luna Max Reasoning | Sep 2026 | Nov 2026 | Official leaderboard |
| 18 | GPT-5.6 Terra | 1,419 ±86.1 | GPT 5.6 Terra Max Reasoning | Jul 2026 | Nov 2026 | Official leaderboard |
| 19 | GPT-5.6 Luna | 1,418 ±86.5 | GPT-5.6 Luna Max Reasoning | Jul 2026 | Nov 2026 | Official leaderboard |
| 20 | Grok 4.6 | 1,399 ±88.3 | Grok 4.6 Xhigh Reasoning | Aug 2026 | Nov 2026 | Official leaderboard |
| 21 | Kimi K3 | 1,393 ±93.3 | Kimi K3 Max Reasoning | Jul 2026 | Nov 2026 | Official leaderboard |
| 22 | | 1,335 ±91.4 | Gemini 3.5 Flash-Lite High Reasoning | Jul 2026 | Nov 2026 | Official leaderboard |
| 23 | Grok 4.5 | 1,334 ±88.3 | Grok 4.5 High Reasoning | Jul 2026 | Nov 2026 | Official leaderboard |
| 24 | Claude Sonnet 5 | 1,309 ±88.6 | Jun 2026 | Nov 2026 | Official leaderboard | |
| 25 | Claude Haiku 5.5 | 1,305 ±91.4 | Oct 2026 | Nov 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Kaggle SVG Arena leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Kaggle SVG Arena leaderboard
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 Coding
- SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
- LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests.
DeepSeek-V4-Pro 93.5%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
- DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
- SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases.
Seed2.1 Pro 59.8%
- Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance.
DeepSeek V4.1 Flash 3,471
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (25 entries).
- Pass Models scored 25 models we track.
- Pass Newest score The newest is from October 2026, for Gemini 4 Carbon.
- Pass Frontier models 7 of the top 10 have a score, led by Gemini 4 Carbon (#3).
- Note Headroom Scored as a rating, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on kaggle.com: 25 rows for models we track 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.