Job BenchBrowse 284 families
Job Bench
Can the model produce useful work in a professional knowledge-work setting?
Version / measure
- Domain
- Knowledge Work
- Ranked models
- 9
- Reported values
- 11
- Reports
- 2 · lab
- Direction
- Higher is better
- Status
- Version not specified
Rankings
Best reported score per model across effort settings
| # | Model | Best setting | Score |
|---|---|---|---|
| 1 | Claude Fable 5Anthropic | maxcost n/a1 value · Jul 17 · source | 57.4% |
| 2 | Muse Spark 1.1Meta | xhighcost n/a1 value · Jul 9 · source | 54.7% |
| 3 | Kimi K3Moonshot AIOW | maxcost n/a1 value · Jul 17 · source | 52.9% |
| 4 | Claude Opus 4.8Anthropic | maxcost n/a2 values · Jul 17 · source | 48.4% |
| 5 | GPT-5.6 SolOpenAI | maxcost n/a1 value · Jul 17 · source | 46.5% |
| 6 | GLM-5.2Z.aiOW | maxcost n/a1 value · Jul 17 · source | 43.4% |
| 7 | GPT-5.5OpenAI | xhighcost n/a2 values · Jul 17 · source | 38.3% |
| 8 | Muse Spark 1.0Meta | reportedcost n/a1 value · Jul 9 · source | 17.0% |
| 9 | Gemini 3.1 ProGoogle | highcost n/a1 value · Jul 9 · source | 15.9% |
Effort curve
Score vs. reported cost. Lines connect complete sweeps only.
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology
Can the model produce useful work in a professional knowledge-work setting?
Professional analysis, document, finance, office, or domain-specific tasks. Higher is better. The value is the percentage reported in this lab's table.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
65 professional tasks; OpenCode harness with Grok 4.3 judge; competitor values from the cited leaderboard.
Method / source ↗