Benchmark Almanac

StoreBench

Claude Fable 5.2 0.83 leads since November 2026
Not in model cards

Agents manage a simulated apparel store in Medusa. They order inventory, change prices, ship purchases, and process refunds as demand changes.

AfterQuery ranks 13 models over 11 tasks, with 99 runs per model. Seven models also ran a separate yearlong experiment under different rules.

Made by
AfterQuery
Released
October 2026
Kind
Running a business
Level
University
Scored
Checked automatically
Answers
Agent task
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Text, Tables → Actions
Interaction
Agentic
Environment
A simulator, Medusa
Items from
Generated
Refresh
One fixed set
Run by
A host
Strongest model tested
Claude Fable 5.2 #2 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
13
Models scored on its own leaderboard

Claude Fable 5.2 leads with 0.83

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. 1 Claude Fable 5.2 0.83
  2. 2 GPT-6 Astra 0.77
  3. 3 Claude Opus 5.5 0.76
  4. 4 Claude Fable 5.1 0.72
  5. 5 GPT-6.1 Sol 0.72
  6. 6 DeepSeek-V4-Pro 0.70
  7. 7 Gemini 4 Argon 0.68
  8. 8 Claude Opus 4.8 0.67
  9. 9 Claude Fable 5 0.63
  10. 10 Qwen 3.8 Max 0.59
  11. 11 Gemini 3.8 Flash 0.55
  12. 12 GPT-5.6 Sol 0.54
  13. 13 Muse Spark 1.2 0.39

Source: Official StoreBench leaderboard

#ModelScore ±SettingDateSource
1 Claude Fable 5.2 0.83 ±0 Nov 2026 Official leaderboard
2 GPT-6 Astra 0.77 0.7 to 0.8 Sep 2026 Official leaderboard
3 Claude Opus 5.5 0.76 ±0 Sep 2026 Official leaderboard
4 Claude Fable 5.1 0.72 0.7 to 0.8 Sep 2026 Official leaderboard
5 GPT-6.1 Sol 0.72 0.7 to 0.8 Sep 2026 Official leaderboard
6 DeepSeek-V4-Pro 0.70 0.7 to 0.7 Apr 2026 Official leaderboard
7 Gemini 4 Argon 0.68 0.6 to 0.7 Sep 2026 Official leaderboard
8 Claude Opus 4.8 0.67 0.6 to 0.7 May 2026 Official leaderboard
9 Claude Fable 5 0.63 ±0 Jun 2026 Official leaderboard
10 Qwen 3.8 Max 0.59 0.5 to 0.6 Aug 2026 Official leaderboard
11 Gemini 3.8 Flash 0.55 0.5 to 0.6 Sep 2026 Official leaderboard
12 GPT-5.6 Sol 0.54 ±0 Jul 2026 Official leaderboard
13 Muse Spark 1.2 0.39 0.3 to 0.4 Aug 2026 Official leaderboard

Rankings by part

We read 11 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as steady, cold-start and supply-shock. Claude Fable 5.2 leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

steady

13 models we track have a score here.

  1. 1 Claude Fable 5.2 0.84
  2. 2 GPT-6 Astra 0.79
  3. 3 Claude Opus 5.5 0.75
  4. 4 DeepSeek-V4-Pro ↑2 0.74
  5. 5 Claude Fable 5.1 ↓1 0.73
  6. 6 Gemini 4 Argon ↑1 0.73
  7. 7 GPT-6.1 Sol ↓2 0.70
  8. 8 Claude Fable 5 ↑1 0.60
  9. 9 Qwen 3.8 Max ↑1 0.58
  10. 10 Claude Opus 4.8 ↓2 0.58

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 Anthropic
Own leaderboard 2 leaders

Source: Official StoreBench 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 2026 2027 0.40 0.60 0.80 2026 2027

Source: Official StoreBench 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 Economic work

All 210 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (13 entries).
  • Pass Models scored 13 models we track.
  • Pass Newest score The newest is from November 2026, for Claude Fable 5.2.
  • Pass Frontier models 6 of the top 10 have a score, led by Claude Fable 5.2 (#2).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on afterquery.com: 13 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