productivity benchmark
Job Bench Leaderboard
Job Bench evaluates AI agents on realistic professional tasks requiring multi-step planning, research, and production of work artifacts.
Updated Sep 5, 2026
Models8
Model coverage8
MetricScore
EvidenceB
Job Bench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelME | Score64.90% | Percentile100.00% | Participants8 | EvidenceC | Evaluated |
| Rank02 | ModelTE | Score61.70% | Percentile85.71% | Participants8 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score55.70% | Percentile71.43% | Participants8 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score55.70% | Percentile57.14% | Participants8 | EvidenceC | Evaluated |
| Rank05 | ModelME | Score54.70% | Percentile42.86% | Participants8 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score53.40% | Percentile28.57% | Participants8 | EvidenceC | Evaluated |
| Rank07 | ModelMA | Score52.90% | Percentile14.29% | Participants8 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score33.40% | Percentile0.00% | Participants8 | EvidenceC | Evaluated |
Job Bench Highlights
The leading models and scores on this benchmark.
Job Bench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Job Bench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Job Bench?
What Job Bench measures and how its scores work.
Job Bench is a productivity benchmark for evaluating AI agents on realistic professional tasks.
It measures performance using the Score metric, reported as a ratio, on tasks requiring multi-step planning, research, and production of work artifacts.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Job Bench
- Modality
- text
- Primary category
- productivity
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Job Bench.
Which model scores highest on Job Bench?
Muse Spark 1.3 is currently ranked first with 64.90%.
What are the top three models on Job Bench?
The current leaders are Muse Spark 1.3 (64.90%), Hy4 preview (61.70%), and Qwen3.8-Flash-Next (55.70%).
Which Job Bench model has the lowest official input price?
Qwen3.8 Flash has the lowest matched official input price at $0.15 input / $0.47 output per 1M tokens.
Which models are fastest among Job Bench results?
The fastest matched records are Qwen3.8 Max (60.87 tok/s via DeepInfra), Muse Spark 1.1 (14.00 tok/s via Meta Model API), and Muse Spark 1.3 (8.44 tok/s via Meta Model API).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.