Skip to content

Benchmark

Workspace-Bench 1.0 · Full

Scores are percentages. Higher is better.

Models measured
6
Scores recorded
6
Sources
1
IQ weight
No weight published

Score distribution

65.1%
Mean
66.8%
Median
3.2%
Std dev
61.4%
10th percentile
68.7%
90th percentile
60.2%
Min
60.2%68.7%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude Fable 5Qwen3.8 官方模型卡对照表 · Workspace-Bench 1.0· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.68.7%
2Qwen3.8 MaxQwen3.8 官方模型卡对照表 · Workspace-Bench 1.0· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.67.7%
3Claude Opus 4.8Qwen3.8 官方模型卡对照表 · Workspace-Bench 1.0· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.66.8%
4GPT-5.6 SolQwen3.8 官方模型卡对照表 · Workspace-Bench 1.0· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65.6%
5Qwen3.7 MaxQwen3.8 官方模型卡对照表 · Workspace-Bench 1.0· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.61.4%
6Hy4 previewofficial model-card appendix· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.60.2%

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.