Skip to content

Benchmark

E-Commerce Bench · Drawdown / peak assets

Lower scores are better.

Models and systems measured
20
Scores recorded
21
Sources
1
IQ weight
0.35

Score distribution

0.394
Mean
0.36
Median
0.234
Std dev
0.141
10th percentile
0.688
90th percentile
0.127
Min
0.1270.979
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.35 for chat models, measured over 17 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#Model or systemScore
1GLM 5.2benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · high reasoning · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.127
2Claude Opus 4.8benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · max reasoning · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.13
3Claude Fable 5benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · max reasoning · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.141
4Qwen3.8 Maxbenchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · thinking enabled where supported; effort not specified · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.0.172
5Claude Opus 4.7benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · max reasoning · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.189
6GLM 5.1benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · thinking enabled where supported; effort not specified · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.231
7Kimi K3benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · thinking enabled where supported; effort not specified · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.247
8GPT-5.6 Solbenchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · max reasoning · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.278
9GLM 5.2benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · max reasoning · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.36
10Kimi K2.6benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · thinking enabled where supported; effort not specified · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.377
11Qwen3.7 Maxbenchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · thinking enabled where supported; effort not specified · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.0.433
12Gemini 3.5 Flashbenchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · thinking enabled where supported; effort not specified · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.45
13GLM 5.3 Flashbenchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · max reasoning · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.533
14Qwen3.6 Plusbenchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · thinking enabled where supported; effort not specified · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.0.583
15Claude Opus 4.6benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · max reasoning · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.587
16GPT 5.5benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · thinking enabled where supported; effort not specified · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.591
17Gemini 3.1 Pro Previewbenchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · thinking enabled where supported; effort not specified · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.688
18GLM 5.3benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · max reasoning · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.78

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
DeepSeek V4 Pro Preview (E-Commerce Bench)benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · max reasoning · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs0.166
Qwen3.5 Plusbenchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · thinking enabled where supported; effort not specified · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.0.979
Qwen3.8 Max Preview (E-Commerce Bench)benchmark-owner 365-day merchant simulation · five independent episodes · up to four stores · initial balance ¥100,000 · thinking enabled where supported; effort not specified · exact API snapshot not stated for unversioned labels· Reported by E-Commerce Bench authors / Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.0.242

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.