Skip to content

Benchmark

E-Commerce Bench · CSE+ · honest-deal negotiation

Higher scores are better.

Models and systems measured
20
Scores recorded
21
Sources
1
IQ weight
0.83

Score distribution

0.677
Mean
0.662
Median
0.055
Std dev
0.625
10th percentile
0.772
90th percentile
0.596
Min
0.5960.811
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.83 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
1Claude 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 docs0.811
2Gemini 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 docs0.777
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 docs0.772
4GLM 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 docs0.729
5GPT 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 docs0.7
6GLM 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 docs0.693
7GPT-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 docs0.672
8GLM 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 docs0.668
9Claude 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 docs0.662
10GLM 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 docs0.662
11Gemini 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 docs0.66
12Qwen3.8 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.0.66
13Claude 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 docs0.649
14GLM 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 docs0.632
15Kimi 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 docs0.632
16Qwen3.6 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.0.625
17Qwen3.7 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.0.616
18Kimi 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 docs0.596

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 docs0.654
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.0.625
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.0.713

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.