Benchmark Almanac

LegacyShop

Claude Opus 5.5 0.91 leads since October 2026
Not in model cards

Models maintain a Python repository for an online shop. Tasks test bug fixes, memory reasoning, complexity analysis, and whether to ask for clarification.

Kaggle publishes scores for 14 distinct model versions.

Released
October 2026
Kind
Fixing real repositories
Level
University
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code, Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
October 2026
Scores refreshed
November 20th, 2026
14
Entries on its own leaderboard, 13 models we track

Claude Opus 5.5 leads with 0.91 Claude Opus 5.5 leads with 0.91

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. 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.

  1. 1 Claude Opus 5.5 0.91
  2. 2 Claude Sonnet 5.5 0.89
  3. 3 Gemini 3.1 Pro 0.85
  4. 4 Gemini 3.8 Flash 0.84
  5. 5 Claude Haiku 5.5 0.80
  6. 6 GPT-6 Luna 0.79
  7. 7 GPT-6 Astra 0.77
  8. 8 GLM-5 0.71
  9. 9 GPT-6.1 Sol 0.70
  10. 10 Gemma 4 31B IT 0.70
  11. 11 DeepSeek-R1 May 2025 0.63
  12. 12 GPT-5.6 Terra 0.61
  13. 13 Grok 4.20 reasoning 0.45
  14. 14 Qwen 3 Next 80B Instruct 0.38

Source: Official LegacyShop leaderboard

#EntryScoreSettingReleasedRun onSource
1 Claude Opus 5.5 0.91 Sep 2026 Oct 2026 Official leaderboard
2 Claude Sonnet 5.5 0.89 Sep 2026 Oct 2026 Official leaderboard
3 Gemini 3.1 Pro 0.85 Feb 2026 Oct 2026 Official leaderboard
4 Gemini 3.8 Flash 0.84 Sep 2026 Oct 2026 Official leaderboard
5 Claude Haiku 5.5 0.80 Oct 2026 Oct 2026 Official leaderboard
6 GPT-6 Luna 0.79 Sep 2026 Oct 2026 Official leaderboard
7 GPT-6 Astra 0.77 Sep 2026 Oct 2026 Official leaderboard
8 GLM-5 0.71 Feb 2026 Oct 2026 Official leaderboard
9 GPT-6.1 Sol 0.70 Sep 2026 Oct 2026 Official leaderboard
10 Gemma 4 31B IT 0.70 Apr 2026 Oct 2026 Official leaderboard
11 DeepSeek-R1 May 2025 0.63 May 2025 Oct 2026 Official leaderboard
12 GPT-5.6 Terra 0.61 Jul 2026 Oct 2026 Official leaderboard
13 Grok 4.20 0.45 reasoning Feb 2026 Oct 2026 Official leaderboard
14 Qwen 3 Next 80B Instruct 0.38 Oct 2026 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 Claude Opus 5.5 0.91 Sep 2026 Oct 2026 Official leaderboard
2 Claude Sonnet 5.5 0.89 Sep 2026 Oct 2026 Official leaderboard
3 Gemini 3.1 Pro 0.85 Feb 2026 Oct 2026 Official leaderboard
4 Gemini 3.8 Flash 0.84 Sep 2026 Oct 2026 Official leaderboard
5 Claude Haiku 5.5 0.80 Oct 2026 Oct 2026 Official leaderboard
6 GPT-6 Luna 0.79 Sep 2026 Oct 2026 Official leaderboard
7 GPT-6 Astra 0.77 Sep 2026 Oct 2026 Official leaderboard
8 GLM-5 0.71 Feb 2026 Oct 2026 Official leaderboard
9 GPT-6.1 Sol 0.70 Sep 2026 Oct 2026 Official leaderboard
10 Gemma 4 31B IT 0.70 Apr 2026 Oct 2026 Official leaderboard
11 DeepSeek-R1 May 2025 0.63 May 2025 Oct 2026 Official leaderboard
12 GPT-5.6 Terra 0.61 Jul 2026 Oct 2026 Official leaderboard
13 Grok 4.20 0.45 reasoning Feb 2026 Oct 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 LegacyShop 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
0.40 0.60 0.80 1.00 2025 2026 0.40 0.60 0.80 1.00 2025 2026

Source: Official LegacyShop 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 13 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from October 2026, for Claude Haiku 5.5.
  • Pass Frontier models 4 of the top 10 have a score, led by GPT-6 Astra (#4).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on kaggle.com: 13 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