productivity benchmark
CoWorkBench Leaderboard
CoWorkBench is Qwen's internal cowork benchmark for evaluating long-horizon office and productivity agent tasks across domains such as computer science, finance, law, and medicine.
Updated Sep 5, 2026
Models6
Model coverage6
MetricScore
EvidenceB
CoWorkBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score74.80% | Percentile100.00% | Participants6 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score73.90% | Percentile80.00% | Participants6 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score73.90% | Percentile60.00% | Participants6 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score70.70% | Percentile40.00% | Participants6 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score67.20% | Percentile20.00% | Participants6 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score65.10% | Percentile0.00% | Participants6 | EvidenceC | Evaluated |
CoWorkBench Highlights
The leading models and scores on this benchmark.
CoWorkBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for CoWorkBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is CoWorkBench?
What CoWorkBench measures and how its scores work.
CoWorkBench is Qwen's internal cowork benchmark.
It measures performance on long-horizon office and productivity agent tasks across domains such as computer science, finance, law, and medicine, using the Score metric as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CoWorkBench
- 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 CoWorkBench.
Which model scores highest on CoWorkBench?
Qwen3.8 Max is currently ranked first with 74.80%.
What are the top three models on CoWorkBench?
The current leaders are Qwen3.8 Max (74.80%), Qwen3.8-Flash-Next (73.90%), and Qwen3.8 Flash (73.90%).
Which CoWorkBench 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 CoWorkBench results?
The fastest matched records are Qwen3.8 Max (60.87 tok/s via DeepInfra).
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.