Benchmark
Workspace-Bench 1.0 · Full
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- 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
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude 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% |
| 2 | Qwen3.8 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% |
| 3 | Claude 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% |
| 4 | GPT-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% |
| 5 | Qwen3.7 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% |
| 6 | Hy4 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% |