Benchmark Almanac

Kaggle Explode Arena

GPT-6 Astra 1,712 leads since October 2026
Not in model cards

Models build interactive exploded views of objects in three.js. A submission must render a self contained page where the viewer can separate the parts. Votes determine the arena rating.

Kaggle publishes scores for 14 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
Items from
Live play or votes
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
14
Models scored on its own leaderboard

GPT-6 Astra leads with 1,712

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.

Bars start at 1,200.

  1. 1 GPT-6 Astra GPT-6 Astra Max Reasoning 1,712
  2. 2 Gemini 4 Carbon Gemini 4 Carbon High Reasoning 1,703
  3. 3 GPT-6.1 Sol GPT-6.1 Sol Max Reasoning 1,660
  4. 4 Claude Opus 5.5 Claude Opus 5.5 Max Reasoning 1,656
  5. 5 Gemini 4 Argon Gemini 4 Argon High Reasoning 1,621
  6. 6 Claude Fable 5.1 Claude Fable 5.1 Max Reasoning 1,489
  7. 7 Qwen 3.8 Max Qwen 3.8 Max Xhigh Reasoning 1,483
  8. 8 GLM-5.3 GLM-5.3 Max Reasoning 1,481
  9. 9 Gemini 3.8 Flash Gemini 3.8 Flash High Reasoning 1,437
  10. 10 DeepSeek V4.1 Flash Deepseek V4.1 Flash High Reasoning 1,414
  11. 11 Grok 4.6 Grok 4.6 Xhigh Reasoning 1,389
  12. 12 Grok 4.7 Grok 4.7 Xhigh Reasoning 1,372
  13. 13 Kimi K3 Kimi K3 Max Reasoning 1,366
  14. 14 Claude Sonnet 5 1,253

Source: Official Kaggle Explode Arena leaderboard

#ModelScore ±SettingReleasedRun onSource
1 GPT-6 Astra 1,712 ±122.4 GPT-6 Astra Max Reasoning Sep 2026 Nov 2026 Official leaderboard
2 Gemini 4 Carbon 1,703 ±153.4 Gemini 4 Carbon High Reasoning Oct 2026 Nov 2026 Official leaderboard
3 GPT-6.1 Sol 1,660 ±121.2 GPT-6.1 Sol Max Reasoning Sep 2026 Nov 2026 Official leaderboard
4 Claude Opus 5.5 1,656 ±119.9 Claude Opus 5.5 Max Reasoning Sep 2026 Nov 2026 Official leaderboard
5 Gemini 4 Argon 1,621 ±124.7 Gemini 4 Argon High Reasoning Sep 2026 Nov 2026 Official leaderboard
6 Claude Fable 5.1 1,489 ±118.4 Claude Fable 5.1 Max Reasoning Sep 2026 Nov 2026 Official leaderboard
7 Qwen 3.8 Max 1,483 ±122 Qwen 3.8 Max Xhigh Reasoning Aug 2026 Nov 2026 Official leaderboard
8 GLM-5.3 1,481 ±117.7 GLM-5.3 Max Reasoning Aug 2026 Nov 2026 Official leaderboard
9 Gemini 3.8 Flash 1,437 ±118.8 Gemini 3.8 Flash High Reasoning Sep 2026 Nov 2026 Official leaderboard
10 DeepSeek V4.1 Flash 1,414 ±118.6 Deepseek V4.1 Flash High Reasoning Sep 2026 Nov 2026 Official leaderboard
11 Grok 4.6 1,389 ±129.3 Grok 4.6 Xhigh Reasoning Aug 2026 Nov 2026 Official leaderboard
12 Grok 4.7 1,372 ±121 Grok 4.7 Xhigh Reasoning Sep 2026 Nov 2026 Official leaderboard
13 Kimi K3 1,366 ±131.5 Kimi K3 Max Reasoning Jul 2026 Nov 2026 Official leaderboard
14 Claude Sonnet 5 1,253 ±172 Jun 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.

OpenAI
Own leaderboard 1 leader
GPT-6 Astra 1,712

Source: Official Kaggle Explode 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
1,200 1,400 1,600 1,800 2026 2027 1,200 1,400 1,600 1,800 2026 2027

Source: Official Kaggle Explode 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 (14 entries).
  • Pass Models scored 14 models we track.
  • Pass Newest score The newest is from October 2026, for Gemini 4 Carbon.
  • Pass Frontier models 6 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: 14 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