Benchmark Almanac

Kaggle SVG Arena

Claude Opus 5.5 1,699 leads since October 2026
Not in model cards

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
In and out
Text → Code
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
25
Models scored on its own leaderboard

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.

Source: Official Kaggle SVG Arena leaderboard

#ModelScore ±SettingReleasedRun onSource
1 Claude Opus 5.5 1,699 ±90.1 Claude Opus 5.5 Max Reasoning Sep 2026 Nov 2026 Official leaderboard
2 Gemini 4 Argon 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 Gemini 4 Carbon 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 Gemini 3.8 Flash 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 Qwen 3.8 Max 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 Gemini 3.6 Flash 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 Gemini 3.5 Flash-Lite 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.

Anthropic
Own leaderboard 1 leader

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.

Plot with other benchmarks
On the benchmark’s own leaderboard
1,300 1,400 1,500 1,600 1,700 2026 2027 1,300 1,400 1,500 1,600 1,700 2026 2027

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

All 523 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.

How we check