agents benchmark
QwenSWEBench Leaderboard
QwenSWEBench is Qwen's software-engineering agent benchmark for repository-level issue resolution.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
QwenSWEBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score80.70% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score79.00% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
QwenSWEBench Highlights
The leading models and scores on this benchmark.
QwenSWEBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for QwenSWEBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is QwenSWEBench?
What QwenSWEBench measures and how its scores work.
QwenSWEBench is a benchmark for software-engineering agents that evaluates repository-level issue resolution.
It measures repository-level issue resolution using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- QwenSWEBench
- Modality
- text
- Primary category
- agents
- 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 QwenSWEBench.
Which model scores highest on QwenSWEBench?
Qwen3.8 Max is currently ranked first with 80.70%.
What are the top three models on QwenSWEBench?
The current leaders are Qwen3.8 Max (80.70%) and Qwen3.8-27B (79.00%).
Which QwenSWEBench model has the lowest official input price?
Qwen3.8 Max has the lowest matched official input price at $2.0 input / $6.0 output per 1M tokens.
Which models are fastest among QwenSWEBench 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.