Benchmark Almanac

Kaggle Pelican Arena

Gemini 4 Neon 1,816 leads since November 2026
Not in model cards

Models draw a pelican riding a bicycle in SVG. The arena checks whether each drawing renders and asks people to compare the passing entries.

Kaggle publishes scores for 27 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
November 2026
Scores refreshed
November 20th, 2026
27
Entries on its own leaderboard, 26 models we track

Gemini 4 Neon leads with 1,816 Gemini 4 Neon leads with 1,816

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

Bars start at 1,000.

  1. 1 Gemini 4 Neon Gemini 4 Neon High Reasoning 1,816
  2. 2 GPT-6 Astra GPT-6 Astra Max Reasoning 1,803
  3. 3 GPT-6.1 Sol GPT-6.1 Sol Xhigh Reasoning 1,786
  4. 4 Hydrogen Hydrogen High Reasoning 1,778
  5. 5 Claude Sonnet 5.5 Claude Sonnet 5.5 Max Reasoning 1,727
  6. 6 Claude Opus 5.5 Claude Opus 5.5 Max Reasoning 1,726
  7. 7 Gemini 4 Argon Gemini 4 Argon High Reasoning 1,673
  8. 8 Claude Fable 5.1 Claude Fable 5.1 Max Reasoning 1,665
  9. 9 GPT-6 Sol GPT-6 Sol Max Reasoning 1,661
  10. 10 Gemini 4 Carbon Gemini 4 Carbon High Reasoning 1,650
  11. 11 GPT-5.6 Sol GPT-5.6 Sol Max Reasoning 1,622
  12. 12 Qwen 3.8 Max Qwen 3.8 Max Xhigh Reasoning 1,581
  13. 13 GLM-5.3-Flash 1,573
  14. 14 Gemini 3.8 Flash Gemini 3.8 Flash Medium Reasoning 1,572
  15. 15 Claude Opus 5 Claude Opus 5 Xhigh Reasoning 1,570
  16. 16 GLM-5.3 GLM-5.3 Max Reasoning 1,561
  17. 17 GPT-6 Luna GPT-6 Luna Max Reasoning 1,519
  18. 18 Kimi K3 Kimi K3 Max Reasoning 1,487
  19. 19 Gemini 3.6 Flash Gemini 3.6 Flash Medium Reasoning 1,481
  20. 20 Grok 4.6 Grok 4.6 High Reasoning 1,458
  21. 21 GPT-5.6 Luna GPT-5.6 Luna Max Reasoning 1,398
  22. 22 Grok 4.5 Grok 4.5 High Reasoning 1,340
  23. 23 GPT-5.6 Terra GPT 5.6 Terra Max Reasoning 1,320
  24. 24 Claude Haiku 5.5 1,305
  25. 25 Grok 4.7 Grok 4.7 Xhigh Reasoning 1,291
  26. 26 Claude Sonnet 5 1,215
  27. 27 Gemini 3.5 Flash-Lite Gemini 3.5 Flash-Lite High Reasoning 1,165

Source: Official Kaggle Pelican Arena leaderboard

Source: Official Kaggle Pelican Arena leaderboard

#EntryScore ±SettingReleasedRun onSource
1 Gemini 4 Neon 1,816 ±190.4 Gemini 4 Neon High Reasoning Nov 2026 Nov 2026 Official leaderboard
2 GPT-6 Astra 1,803 ±60.3 GPT-6 Astra Max Reasoning Sep 2026 Nov 2026 Official leaderboard
3 GPT-6.1 Sol 1,786 ±59.4 GPT-6.1 Sol Xhigh Reasoning Sep 2026 Nov 2026 Official leaderboard
4 Hydrogen 1,778 ±123.4 Hydrogen High Reasoning Nov 2026 Official leaderboard
5 Claude Sonnet 5.5 1,727 ±61.6 Claude Sonnet 5.5 Max Reasoning Sep 2026 Nov 2026 Official leaderboard
6 Claude Opus 5.5 1,726 ±62 Claude Opus 5.5 Max Reasoning Sep 2026 Nov 2026 Official leaderboard
7 Gemini 4 Argon 1,673 ±56.2 Gemini 4 Argon High Reasoning Sep 2026 Nov 2026 Official leaderboard
8 Claude Fable 5.1 1,665 ±56.1 Claude Fable 5.1 Max Reasoning Sep 2026 Nov 2026 Official leaderboard
9 GPT-6 Sol 1,661 ±56.1 GPT-6 Sol Max Reasoning Sep 2026 Nov 2026 Official leaderboard
10 Gemini 4 Carbon 1,650 ±59.8 Gemini 4 Carbon High Reasoning Oct 2026 Nov 2026 Official leaderboard
11 GPT-5.6 Sol 1,622 ±55.3 GPT-5.6 Sol Max Reasoning Jul 2026 Nov 2026 Official leaderboard
12 Qwen 3.8 Max 1,581 ±54.9 Qwen 3.8 Max Xhigh Reasoning Aug 2026 Nov 2026 Official leaderboard
13 GLM-5.3-Flash 1,573 ±54.8 Aug 2026 Nov 2026 Official leaderboard
14 Gemini 3.8 Flash 1,572 ±52.4 Gemini 3.8 Flash Medium Reasoning Sep 2026 Nov 2026 Official leaderboard
15 Claude Opus 5 1,570 ±54.7 Claude Opus 5 Xhigh Reasoning Jul 2026 Nov 2026 Official leaderboard
16 GLM-5.3 1,561 ±54.5 GLM-5.3 Max Reasoning Aug 2026 Nov 2026 Official leaderboard
17 GPT-6 Luna 1,519 ±54.6 GPT-6 Luna Max Reasoning Sep 2026 Nov 2026 Official leaderboard
18 Kimi K3 1,487 ±54.6 Kimi K3 Max Reasoning Jul 2026 Nov 2026 Official leaderboard
19 Gemini 3.6 Flash 1,481 ±54.2 Gemini 3.6 Flash Medium Reasoning Jul 2026 Nov 2026 Official leaderboard
20 Grok 4.6 1,458 ±58.2 Grok 4.6 High Reasoning Aug 2026 Nov 2026 Official leaderboard
21 GPT-5.6 Luna 1,398 ±54.9 GPT-5.6 Luna Max Reasoning Jul 2026 Nov 2026 Official leaderboard
22 Grok 4.5 1,340 ±55.3 Grok 4.5 High Reasoning Jul 2026 Nov 2026 Official leaderboard
23 GPT-5.6 Terra 1,320 ±56.3 GPT 5.6 Terra Max Reasoning Jul 2026 Nov 2026 Official leaderboard
24 Claude Haiku 5.5 1,305 ±56.1 Oct 2026 Nov 2026 Official leaderboard
25 Grok 4.7 1,291 ±56.6 Grok 4.7 Xhigh Reasoning Sep 2026 Nov 2026 Official leaderboard
26 Claude Sonnet 5 1,215 ±59.1 Jun 2026 Nov 2026 Official leaderboard
27 Gemini 3.5 Flash-Lite 1,165 ±61.5 Gemini 3.5 Flash-Lite High Reasoning Jul 2026 Nov 2026 Official leaderboard
#ModelScore ±SettingReleasedRun onSource
1 Gemini 4 Neon 1,816 ±190.4 Gemini 4 Neon High Reasoning Nov 2026 Nov 2026 Official leaderboard
2 GPT-6 Astra 1,803 ±60.3 GPT-6 Astra Max Reasoning Sep 2026 Nov 2026 Official leaderboard
3 GPT-6.1 Sol 1,786 ±59.4 GPT-6.1 Sol Xhigh Reasoning Sep 2026 Nov 2026 Official leaderboard
4 Claude Sonnet 5.5 1,727 ±61.6 Claude Sonnet 5.5 Max Reasoning Sep 2026 Nov 2026 Official leaderboard
5 Claude Opus 5.5 1,726 ±62 Claude Opus 5.5 Max Reasoning Sep 2026 Nov 2026 Official leaderboard
6 Gemini 4 Argon 1,673 ±56.2 Gemini 4 Argon High Reasoning Sep 2026 Nov 2026 Official leaderboard
7 Claude Fable 5.1 1,665 ±56.1 Claude Fable 5.1 Max Reasoning Sep 2026 Nov 2026 Official leaderboard
8 GPT-6 Sol 1,661 ±56.1 GPT-6 Sol Max Reasoning Sep 2026 Nov 2026 Official leaderboard
9 Gemini 4 Carbon 1,650 ±59.8 Gemini 4 Carbon High Reasoning Oct 2026 Nov 2026 Official leaderboard
10 GPT-5.6 Sol 1,622 ±55.3 GPT-5.6 Sol Max Reasoning Jul 2026 Nov 2026 Official leaderboard
11 Qwen 3.8 Max 1,581 ±54.9 Qwen 3.8 Max Xhigh Reasoning Aug 2026 Nov 2026 Official leaderboard
12 GLM-5.3-Flash 1,573 ±54.8 Aug 2026 Nov 2026 Official leaderboard
13 Gemini 3.8 Flash 1,572 ±52.4 Gemini 3.8 Flash Medium Reasoning Sep 2026 Nov 2026 Official leaderboard
14 Claude Opus 5 1,570 ±54.7 Claude Opus 5 Xhigh Reasoning Jul 2026 Nov 2026 Official leaderboard
15 GLM-5.3 1,561 ±54.5 GLM-5.3 Max Reasoning Aug 2026 Nov 2026 Official leaderboard
16 GPT-6 Luna 1,519 ±54.6 GPT-6 Luna Max Reasoning Sep 2026 Nov 2026 Official leaderboard
17 Kimi K3 1,487 ±54.6 Kimi K3 Max Reasoning Jul 2026 Nov 2026 Official leaderboard
18 Gemini 3.6 Flash 1,481 ±54.2 Gemini 3.6 Flash Medium Reasoning Jul 2026 Nov 2026 Official leaderboard
19 Grok 4.6 1,458 ±58.2 Grok 4.6 High Reasoning Aug 2026 Nov 2026 Official leaderboard
20 GPT-5.6 Luna 1,398 ±54.9 GPT-5.6 Luna Max Reasoning Jul 2026 Nov 2026 Official leaderboard
21 Grok 4.5 1,340 ±55.3 Grok 4.5 High Reasoning Jul 2026 Nov 2026 Official leaderboard
22 GPT-5.6 Terra 1,320 ±56.3 GPT 5.6 Terra Max Reasoning Jul 2026 Nov 2026 Official leaderboard
23 Claude Haiku 5.5 1,305 ±56.1 Oct 2026 Nov 2026 Official leaderboard
24 Grok 4.7 1,291 ±56.6 Grok 4.7 Xhigh Reasoning Sep 2026 Nov 2026 Official leaderboard
25 Claude Sonnet 5 1,215 ±59.1 Jun 2026 Nov 2026 Official leaderboard
26 Gemini 3.5 Flash-Lite 1,165 ±61.5 Gemini 3.5 Flash-Lite High Reasoning Jul 2026 Nov 2026 Official leaderboard

More effort adds a median 120 elo

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
GPT-6 Astra
GPT-6 Astra… GPT-6 Astra…
1,803
GPT-6.1 Sol
GPT-6.1 Sol…
1,786
Claude Sonnet 5.5
Claude Sonn… Claude Sonn…
1,727
Claude Opus 5.5
Claude Opus… Claude Opus…
1,726
Gemini 4 Argon
Gemini 4 Ar…
1,673
Claude Fable 5.1
Claude Fabl… Claude Fabl… Claude Fabl…
1,665
GPT-6 Sol
GPT-6 Sol H… GPT-6 Sol M…
1,661
GPT-5.6 Sol
GPT-5.6 Sol… GPT-5.6 Sol… GPT-5.6 Sol…
1,622
Qwen 3.8 Max
Qwen 3.8 Ma… Qwen 3.8 Ma… Qwen 3.8 Ma…
1,581
Gemini 3.8 Flash
Gemini 3.8 … Gemini 3.8 …
1,572
Claude Opus 5
Claude Opus… Claude Opus… Claude Opus…
1,570
GLM-5.3
GLM-5.3 Med… GLM-5.3 Max…
1,561

Source: Official Kaggle Pelican Arena leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Gemini 4 Neon Gemini 4 Neon High Reasoning 1,816
GPT-6 Astra GPT-6 Astra Max Reasoning 1,803
GPT-6.1 Sol GPT-6.1 Sol Xhigh Reasoning 1,786
GPT-6.1 Sol GPT-6.1 Sol Max Reasoning 1,783
GPT-6 Astra GPT-6 Astra High Reasoning 1,764
GPT-6 Astra GPT-6 Astra Low Reasoning 1,740
Claude Sonnet 5.5 Claude Sonnet 5.5 Max Reasoning 1,727
Claude Opus 5.5 Claude Opus 5.5 Max Reasoning 1,726
Claude Opus 5.5 Claude Opus 5.5 Xhigh Reasoning 1,696
Gemini 4 Argon Gemini 4 Argon High Reasoning 1,673
Claude Fable 5.1 Claude Fable 5.1 Max Reasoning 1,665
GPT-6 Sol GPT-6 Sol Max Reasoning 1,661
Gemini 4 Carbon Gemini 4 Carbon High Reasoning 1,650
Gemini 4 Argon Gemini 4 Argon Low Reasoning 1,633
GPT-5.6 Sol GPT-5.6 Sol Max Reasoning 1,622
Qwen 3.8 Max Qwen 3.8 Max Xhigh Reasoning 1,581
GLM-5.3-Flash 1,573
Gemini 3.8 Flash Gemini 3.8 Flash Medium Reasoning 1,572
Claude Opus 5 Claude Opus 5 Xhigh Reasoning 1,570
GPT-5.6 Sol GPT-5.6 Sol Xhigh Reasoning 1,565
Gemini 3.8 Flash Gemini 3.8 Flash High Reasoning 1,563
GLM-5.3 GLM-5.3 Max Reasoning 1,561
Claude Opus 5 Claude Opus 5 Max Reasoning 1,558
Claude Opus 5.5 Claude Opus 5.5 High Reasoning 1,557
GPT-6 Sol GPT-6 Sol High Reasoning 1,541
Claude Opus 5.5 Claude Opus 5.5 Medium Reasoning 1,541
GPT-6 Luna GPT-6 Luna Max Reasoning 1,519
Qwen 3.8 Max 1,497
Claude Fable 5.1 Claude Fable 5.1 High Reasoning 1,493
Kimi K3 Kimi K3 Max Reasoning 1,487
Claude Sonnet 5.5 Claude Sonnet 5.5 High Reasoning 1,481
Gemini 3.6 Flash Gemini 3.6 Flash Medium Reasoning 1,481
GLM-5.3 GLM-5.3 High Reasoning 1,474
GPT-5.6 Sol GPT-5.6 Sol Medium Reasoning 1,468
Qwen 3.8 Max Qwen 3.8 Max Medium Reasoning 1,464
Gemini 3.6 Flash Gemini 3.6 Flash High Reasoning 1,460
Grok 4.6 Grok 4.6 High Reasoning 1,458
GPT-5.6 Sol GPT-5.6 Sol High Reasoning 1,449
GPT-6 Luna GPT-6 Luna High Reasoning 1,443
Kimi K3 Kimi K3 Medium Reasoning 1,443
Claude Opus 5 Claude Opus 5 High Reasoning 1,436
GLM-5.3 GLM-5.3 Medium Reasoning 1,434
Claude Fable 5.1 Claude Fable 5.1 Low Reasoning 1,413
Kimi K3 Kimi K3 High Reasoning 1,409
Grok 4.6 Grok 4.6 Xhigh Reasoning 1,406
GPT-5.6 Luna GPT-5.6 Luna Max Reasoning 1,398
Qwen 3.8 Max Qwen 3.8 Max Low Reasoning 1,390
Claude Opus 5 Claude Opus 5 Medium Reasoning 1,376
Grok 4.5 Grok 4.5 High Reasoning 1,340
GPT-5.6 Luna GPT-5.6 Luna XHigh Reasoning 1,323
GPT-5.6 Terra GPT 5.6 Terra Max Reasoning 1,320
Claude Haiku 5.5 1,305
Grok 4.7 Grok 4.7 Xhigh Reasoning 1,291
Gemini 3.8 Flash Gemini 3.8 Flash Low Reasoning 1,284
GPT-5.6 Luna GPT-5.6 Luna High Reasoning 1,264
GPT-5.6 Terra GPT-5.6 Terra Medium Reasoning 1,256
GPT-5.6 Terra GPT-5.6 Terra XHigh Reasoning 1,235
GPT-5.6 Terra GPT-5.6 Terra High Reasoning 1,222
Claude Sonnet 5 1,215
GPT-5.6 Luna GPT-5.6 Luna Medium Reasoning 1,196
Gemini 3.5 Flash-Lite Gemini 3.5 Flash-Lite High Reasoning 1,165

More effort adds a median 120 elo

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
GPT-6 Astra
GPT-6 Astra… GPT-6 Astra…
1,803
GPT-6.1 Sol
GPT-6.1 Sol…
1,786
Claude Sonnet 5.5
Claude Sonn… Claude Sonn…
1,727
Claude Opus 5.5
Claude Opus… Claude Opus…
1,726
Gemini 4 Argon
Gemini 4 Ar…
1,673
Claude Fable 5.1
Claude Fabl… Claude Fabl… Claude Fabl…
1,665
GPT-6 Sol
GPT-6 Sol H… GPT-6 Sol M…
1,661
GPT-5.6 Sol
GPT-5.6 Sol… GPT-5.6 Sol… GPT-5.6 Sol…
1,622
Qwen 3.8 Max
Qwen 3.8 Ma… Qwen 3.8 Ma… Qwen 3.8 Ma…
1,581
Gemini 3.8 Flash
Gemini 3.8 … Gemini 3.8 …
1,572
Claude Opus 5
Claude Opus… Claude Opus… Claude Opus…
1,570
GLM-5.3
GLM-5.3 Med… GLM-5.3 Max…
1,561

Source: Official Kaggle Pelican Arena leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Gemini 4 Neon Gemini 4 Neon High Reasoning 1,816
GPT-6 Astra GPT-6 Astra Max Reasoning 1,803
GPT-6.1 Sol GPT-6.1 Sol Xhigh Reasoning 1,786
GPT-6.1 Sol GPT-6.1 Sol Max Reasoning 1,783
GPT-6 Astra GPT-6 Astra High Reasoning 1,764
GPT-6 Astra GPT-6 Astra Low Reasoning 1,740
Claude Sonnet 5.5 Claude Sonnet 5.5 Max Reasoning 1,727
Claude Opus 5.5 Claude Opus 5.5 Max Reasoning 1,726
Claude Opus 5.5 Claude Opus 5.5 Xhigh Reasoning 1,696
Gemini 4 Argon Gemini 4 Argon High Reasoning 1,673
Claude Fable 5.1 Claude Fable 5.1 Max Reasoning 1,665
GPT-6 Sol GPT-6 Sol Max Reasoning 1,661
Gemini 4 Carbon Gemini 4 Carbon High Reasoning 1,650
Gemini 4 Argon Gemini 4 Argon Low Reasoning 1,633
GPT-5.6 Sol GPT-5.6 Sol Max Reasoning 1,622
Qwen 3.8 Max Qwen 3.8 Max Xhigh Reasoning 1,581
GLM-5.3-Flash 1,573
Gemini 3.8 Flash Gemini 3.8 Flash Medium Reasoning 1,572
Claude Opus 5 Claude Opus 5 Xhigh Reasoning 1,570
GPT-5.6 Sol GPT-5.6 Sol Xhigh Reasoning 1,565
Gemini 3.8 Flash Gemini 3.8 Flash High Reasoning 1,563
GLM-5.3 GLM-5.3 Max Reasoning 1,561
Claude Opus 5 Claude Opus 5 Max Reasoning 1,558
Claude Opus 5.5 Claude Opus 5.5 High Reasoning 1,557
GPT-6 Sol GPT-6 Sol High Reasoning 1,541
Claude Opus 5.5 Claude Opus 5.5 Medium Reasoning 1,541
GPT-6 Luna GPT-6 Luna Max Reasoning 1,519
Qwen 3.8 Max 1,497
Claude Fable 5.1 Claude Fable 5.1 High Reasoning 1,493
Kimi K3 Kimi K3 Max Reasoning 1,487
Claude Sonnet 5.5 Claude Sonnet 5.5 High Reasoning 1,481
Gemini 3.6 Flash Gemini 3.6 Flash Medium Reasoning 1,481
GLM-5.3 GLM-5.3 High Reasoning 1,474
GPT-5.6 Sol GPT-5.6 Sol Medium Reasoning 1,468
Qwen 3.8 Max Qwen 3.8 Max Medium Reasoning 1,464
Gemini 3.6 Flash Gemini 3.6 Flash High Reasoning 1,460
Grok 4.6 Grok 4.6 High Reasoning 1,458
GPT-5.6 Sol GPT-5.6 Sol High Reasoning 1,449
GPT-6 Luna GPT-6 Luna High Reasoning 1,443
Kimi K3 Kimi K3 Medium Reasoning 1,443
Claude Opus 5 Claude Opus 5 High Reasoning 1,436
GLM-5.3 GLM-5.3 Medium Reasoning 1,434
Claude Fable 5.1 Claude Fable 5.1 Low Reasoning 1,413
Kimi K3 Kimi K3 High Reasoning 1,409
Grok 4.6 Grok 4.6 Xhigh Reasoning 1,406
GPT-5.6 Luna GPT-5.6 Luna Max Reasoning 1,398
Qwen 3.8 Max Qwen 3.8 Max Low Reasoning 1,390
Claude Opus 5 Claude Opus 5 Medium Reasoning 1,376
Grok 4.5 Grok 4.5 High Reasoning 1,340
GPT-5.6 Luna GPT-5.6 Luna XHigh Reasoning 1,323
GPT-5.6 Terra GPT 5.6 Terra Max Reasoning 1,320
Claude Haiku 5.5 1,305
Grok 4.7 Grok 4.7 Xhigh Reasoning 1,291
Gemini 3.8 Flash Gemini 3.8 Flash Low Reasoning 1,284
GPT-5.6 Luna GPT-5.6 Luna High Reasoning 1,264
GPT-5.6 Terra GPT-5.6 Terra Medium Reasoning 1,256
GPT-5.6 Terra GPT-5.6 Terra XHigh Reasoning 1,235
GPT-5.6 Terra GPT-5.6 Terra High Reasoning 1,222
Claude Sonnet 5 1,215
GPT-5.6 Luna GPT-5.6 Luna Medium Reasoning 1,196
Gemini 3.5 Flash-Lite Gemini 3.5 Flash-Lite High Reasoning 1,165

2 models have held number one on the official leaderboard since its release in October 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI Google DeepMind
Own leaderboard 2 leaders

Source: Official Kaggle Pelican 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
1,000 1,200 1,400 1,600 1,800 2,000 2026 2027 1,000 1,200 1,400 1,600 1,800 2,000 2026 2027

Source: Official Kaggle Pelican 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 (27 entries).
  • Pass Models scored 26 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from November 2026, for Gemini 4 Neon.
  • Pass Frontier models 7 of the top 10 have a score, led by Gemini 4 Carbon (#3).
  • Note Headroom Scored as an Elo rating, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on kaggle.com: 61 rows for models we track and 1 other entry 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