Benchmark
Workspace-Bench-Lite · Total
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models and systems measured
- 10
- Scores recorded
- 45
- Sources
- 1
- IQ weight
- 0.02
Score distribution
- 45.5%
- Mean
- 45.9%
- Median
- 10.4%
- Std dev
- 34.4%
- 10th percentile
- 57.7%
- 90th percentile
- 13.8%
- Min
This benchmark has a weight of 0.02 for chat models, measured over 7 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 system | Score |
|---|---|---|
| 1 | Claude Opus 4.7OpenClaw · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 66.7% |
| 2 | Claude Opus 4.7ClaudeCode · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 64.7% |
| 3 | Claude Opus 4.7Hermes · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 64.5% |
| 4 | GLM 5.1DeepAgent · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 61% |
| 5 | GLM 5.1Hermes · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 57.7% |
| 6 | GLM 5.1OpenClaw · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 57.5% |
| 7 | Qwen3.6 PlusOpenClaw · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 55.6% |
| 8 | MiniMax M2.7ClaudeCode · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 54.6% |
| 9 | Claude Opus 4.7DeepAgent · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 54.4% |
| 10 | GLM 5.1Codex · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 53.1% |
| 11 | GLM 5.1ClaudeCode · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 52.6% |
| 12 | MiniMax M2.7Hermes · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 52.6% |
| 13 | GPT 5.4ClaudeCode · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 51.8% |
| 14 | Qwen3.6 PlusHermes · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 50.9% |
| 15 | Kimi K2.5Hermes · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 49.1% |
| 16 | Kimi K2.5ClaudeCode · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 48.3% |
| 17 | GPT 5.4Codex · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 47.7% |
| 18 | Qwen3.6 PlusCodex · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 47.3% |
| 19 | GPT 5.4OpenClaw · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 47.1% |
| 20 | Kimi K2.5Codex · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 46.9% |
| 21 | MiniMax M2.7DeepAgent · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 45% |
| 22 | Kimi K2.5OpenClaw · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 44.5% |
| 23 | GPT 5.4Hermes · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 44.3% |
| 24 | MiniMax M2.7OpenClaw · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 44.1% |
| 25 | MiniMax M2.7Codex · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 42.7% |
| 26 | Kimi K2.5DeepAgent · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 41.6% |
| 27 | Qwen3.6 PlusDeepAgent · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 39.4% |
| 28 | Gemini 3.1 Pro PreviewClaudeCode · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 37.5% |
| 29 | Gemini 3.1 Pro PreviewDeepAgent · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 37.2% |
| 30 | GPT 5.4DeepAgent · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 36.2% |
| 31 | Gemini 3.1 Pro PreviewCodex · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 31.9% |
| 32 | Gemini 3.1 Pro PreviewOpenClaw · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 31.6% |
| 33 | Gemini 3.1 Pro PreviewHermes · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 27.1% |
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| Grok 4.3Codex · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 36.9% |
| Grok 4.3DeepAgent · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 13.8% |
| Grok 4.3Hermes · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 36.2% |
| Grok 4.3OpenClaw · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 34.4% |
| Seed-2.0-CodeClaudeCode · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 42.3% |
| Seed-2.0-CodeDeepAgent · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 34.6% |
| Seed-2.0-CodeHermes · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 38.6% |
| Seed-2.0-CodeOpenClaw · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 40.1% |
| Seed-2.0-LiteClaudeCode · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 53% |
| Seed-2.0-LiteDeepAgent · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 36% |
| Seed-2.0-LiteHermes · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 45.9% |
| Seed-2.0-LiteOpenClaw · Workspace-Bench-Lite · 100 tasks · rubric pass rate· Reported by Workspace-Bench· via BenchBoard docs | 46.6% |