productivity benchmark
Job Bench
Job Bench evaluates AI agents on realistic professional tasks that require multi-step planning, research, and production of work artifacts.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
Job Bench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ME | 54.7% | 100.0% | 2 | C | |
| 2 | MA | 52.9% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
Job Bench highlights
The top published results on this benchmark's own scale.
What is Job Bench?
Definition and scoring fields from the benchmark registry.
Job Bench evaluates AI agents on realistic professional tasks that require multi-step planning, research, and production of work artifacts.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Job Bench
- Modality
- text
- Primary category
- productivity
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- job-bench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Job Bench.
Which model scores highest on Job Bench?
Muse Spark 1.1 is currently ranked first with 54.7%.
What does Job Bench measure?
Job Bench evaluates AI agents on realistic professional tasks that require multi-step planning, research, and production of work artifacts.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.